© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13481
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting

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

    mathematical formulas and equations

    oai_token-act-pair · gemini-2.0-flash

    mathematical/scientific equations

    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
     <",
    -0.76
    ScopeManager
    -0.73
     );
    -0.66
     judiciales
    -0.66
    DropColumn
    -0.66
    RegistryLite
    -0.66
     ***!
    -0.65
    -0.62
     ');
    -0.62
    DebuggerNonUser
    -0.62
    POSITIVE LOGITS
    ?}
    0.47
     GR
    0.47
    machung
    0.44
    ...}
    0.44
     Gra
    0.44
    !}
    0.43
     noDo
    0.43
     Pri
    0.42
    ígen
    0.41
    <b>
    0.40
    Activations Density 5.383%
    No Known Activations