© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    words used in formal dialogue, likely in a court setting

    oai_token-act-pair · gemini-2.0-flash

    specific phrases or patterns

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

    Quotation marks

    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
    cato
    -0.49
    RDP
    -0.49
    CodedInputStream
    -0.48
    ேர
    -0.48
     Oats
    -0.45
    reit
    -0.43
    toLocale
    -0.43
    ceğini
    -0.43
    Noc
    -0.43
     oats
    -0.43
    POSITIVE LOGITS
     Савезне
    0.73
    ########.
    0.69
    HostException
    0.60
     CommonModule
    0.58
    ьаж
    0.58
     mustn
    0.57
     MainAxisSize
    0.57
    帖最后由
    0.57
    enumi
    0.56
    각주
    0.55
    Activations Density 2.634%

    No Known Activations