© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11298
    Prev
    Next
    INDEX
    Explanations

    phrases that express a conversational aside

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating parenthetical or additional information

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

    by the way

    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
     виправивши
    -0.80
     doubtnut
    -0.73
     Cæsar
    -0.69
     Monfieur
    -0.67
    Portale
    -0.66
     ―――――
    -0.63
     dafs
    -0.61
     myſelf
    -0.61
     ***/
    -0.60
     Signor
    -0.60
    POSITIVE LOGITS
     btw
    1.37
     BTW
    1.30
     by
    1.15
     кстати
    1.08
     incidentally
    1.07
     By
    0.99
    By
    0.91
    Incident
    0.87
    BTW
    0.85
    by
    0.84
    Activations Density 1.615%

    No Known Activations