© 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. 1702
    Prev
    Next
    INDEX
    Explanations

    code, or phrases implying obligation, conclusion, or instantiation

    oai_token-act-pair · gemini-2.0-flash

    code and errors

    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
     autorytatywna
    -0.74
    Дереккөздер
    -0.73
    AddTagHelper
    -0.71
    expandindo
    -0.66
    contentLoaded
    -0.65
    )";
    -0.65
     faſt
    -0.64
     againſt
    -0.64
    StructEnd
    -0.64
     مشين
    -0.63
    POSITIVE LOGITS
    !
    0.48
     né
    0.47
     rospy
    0.47
    assertEqual
    0.46
    der
    0.46
     porté
    0.45
    companion
    0.45
    CodeAttribute
    0.44
    rendered
    0.44
    antMatchers
    0.44
    Activations Density 0.468%

    No Known Activations