© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2902
    Prev
    Next
    INDEX
    Explanations

    code snippets that appear to be from PHP, possibly related to web development frameworks or templating engines

    oai_token-act-pair · gemini-2.0-flash

    programming or coding syntax elements

    np_token-act-pair-logits · gpt-4o-mini

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasColumnType
    -0.61
     protoimpl
    -0.59
     nonUne
    -0.55
    SpringRunner
    -0.55
    HasMaxLength
    -0.54
    thâu
    -0.54
    wieś
    -0.53
    /*++
    -0.52
    addContainerGap
    -0.49
    ModelAdmin
    -0.49
    POSITIVE LOGITS
    basicConfig
    0.60
    SupportActionBar
    0.59
    numerusform
    0.54
    ervlak
    0.53
     AssemblyCompany
    0.52
    ?>
    0.52
     Advertisement
    0.51
    Locking
    0.50
    bkz
    0.50
    ViewFeatures
    0.50
    Activations Density 1.094%

    No Known Activations