© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12625
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    mathematical/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     GenerationType
    -0.71
    setDo
    -0.69
     soggior
    -0.60
    ghijkl
    -0.57
    igera
    -0.57
    zköz
    -0.57
     numberWith
    -0.56
     joyeux
    -0.55
     isFirst
    -0.55
     révolution
    -0.54
    POSITIVE LOGITS
     continúas
    0.72
    WriteBarrier
    0.57
    TypedDataSet
    0.57
    }")]
    0.56
    msgTypes
    0.56
     chng
    0.54
     Tode
    0.53
    àng
    0.51
    GOTREF
    0.51
    endish
    0.50
    Activations Density 2.141%

    No Known Activations