© 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. 14365
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions that are seeking agreement

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks and question formats

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

    questions

    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
    </tfoot>
    -0.72
    Vidite
    -0.71
     Wayback
    -0.68
    IBAction
    -0.66
    Rhestr
    -0.63
    存于互联网档案馆
    -0.60
    ustus
    -0.59
     iprot
    -0.59
    __))
    -0.59
     وتسجيلات
    -0.57
    POSITIVE LOGITS
    ?
    0.73
    ?!
    0.59
     zanahoria
    0.57
    ?(
    0.55
    !?
    0.54
    ؟
    0.52
    ?!?
    0.52
    ?!?!
    0.50
    ?…
    0.50
    +#+
    0.49
    Activations Density 1.566%

    No Known Activations