© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3212
    Prev
    Next
    INDEX
    Explanations

    terms related to health and/or medicine, including sleep, diet, and hormones

    oai_token-act-pair · gemini-2.0-flash

    Physiology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Signalez
    -0.65
    ритори
    -0.63
    itinéraire
    -0.63
    svet
    -0.63
     surla
    -0.63
    rawDesc
    -0.62
    dataIndex
    -0.61
     विश्वसनीयता
    -0.57
     ſmall
    -0.57
     Verſ
    -0.56
    POSITIVE LOGITS
    İstinadlar
    0.55
     level
    0.49
    Bronnen
    0.44
    })->
    0.42
    ).__
    0.42
    })*/
    0.41
    KHR
    0.41
    ->$
    0.40
    Jegyzetek
    0.40
    Билгалдахарш
    0.40
    Activations Density 3.354%

    No Known Activations