© 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. 12833
    Prev
    Next
    INDEX
    Explanations

    phrases from an Asian language involving shouting or roaring

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks and specific words following actions

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

    Dialogue or narration

    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
    AddTagHelper
    -1.06
    MLLoader
    -0.96
     للمعارف
    -0.95
     itſelf
    -0.89
     oprot
    -0.86
    awtextra
    -0.85
     @"/
    -0.85
    __*/
    -0.83
    новништво
    -0.82
    IVEREF
    -0.81
    POSITIVE LOGITS
    :
    0.50
     plan
    0.50
     kö
    0.50
    ,
    0.48
     term
    0.48
     with
    0.44
     
    0.42
    ERO
    0.41
    ुप
    0.41
     mode
    0.40
    Activations Density 0.544%

    No Known Activations