© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 322
    Prev
    Next
    INDEX
    Explanations

    code snippets and mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    sum or any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AccessFile
    -0.60
     whiteColor
    -0.58
    icksburg
    -0.57
    KURZBESCHREIBUNG
    -0.57
    وردار
    -0.56
    newtheorem
    -0.55
    脚注の使い方
    -0.53
     ddelweddau
    -0.52
     الحره
    -0.51
    readystatechange
    -0.50
    POSITIVE LOGITS
    essoal
    0.56
    ípios
    0.55
    createComponent
    0.48
    oa̍t
    0.47
    المكان
    0.47
     الاطلاع
    0.46
     Administrativna
    0.46
    getJSONArray
    0.45
     unplayable
    0.45
    Descripció
    0.45
    Activations Density 2.277%

    No Known Activations