© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3813
    Prev
    Next
    INDEX
    Explanations

    phrases that describe situations or perceptions

    oai_token-act-pair · gemini-2.0-flash

    technical/argumentative context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    principalTable
    -0.71
     beginnetje
    -0.70
     betweenstory
    -0.69
    ValueGenerated
    -0.69
     AssemblyCulture
    -0.61
    GTCX
    -0.59
     Keny
    -0.54
    PyExc
    -0.52
    mögens
    -0.52
    /******/
    -0.52
    POSITIVE LOGITS
    WriteLiteral
    0.53
    __':
    0.52
    ine
    0.51
    WaitGroup
    0.50
    mak
    0.50
    jda
    0.49
    uns
    0.47
    buch
    0.46
    mybatisplus
    0.46
    há
    0.45
    Activations Density 1.703%

    No Known Activations