© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11300
    Prev
    Next
    INDEX
    Explanations

    source code and code documentation

    oai_token-act-pair · gemini-2.0-flash

    code parameters

    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
    /**
    -0.71
    PreferredItem
    -0.69
    )_/¯
    -0.65
     onPostExecute
    -0.64
     }</
    -0.63
     []:
    -0.60
     {}));
    -0.58
    êmio
    -0.57
    Vielen
    -0.56
    itects
    -0.54
    POSITIVE LOGITS
     Normdatei
    0.58
     context
    0.52
    Geplaatst
    0.51
    Portály
    0.48
    context
    0.47
     lang
    0.46
    protoc
    0.46
     tắt
    0.45
    RTEX
    0.45
     виправивши
    0.45
    Activations Density 37.696%

    No Known Activations