© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8895
    Prev
    Next
    INDEX
    Explanations

    parts of code snippets with loops, variable declarations and standard output

    oai_token-act-pair · gemini-2.0-flash

    uncommon character sequences or special formatting

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

    code, system, programming

    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
    XmlAccessType
    -0.57
    ặng
    -0.52
    styleType
    -0.51
    imab
    -0.51
    Portály
    -0.51
    tight
    -0.51
    iecie
    -0.51
    iNdEx
    -0.51
    TypedDataSet
    -0.50
    migrationBuilder
    -0.49
    POSITIVE LOGITS
    usercontent
    0.60
    MENAFN
    0.60
    ParallelGroup
    0.58
    endpush
    0.52
     leaſt
    0.51
     raiſ
    0.51
     ſtand
    0.50
     myſelf
    0.50
     cauſe
    0.50
     faſt
    0.49
    Activations Density 6.904%

    No Known Activations