© 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. 1255
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms used in ultrasound imaging and nerve blocks

    oai_token-act-pair · gemini-2.0-flash

    sonography

    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
    PreferredItem
    -0.92
     createSlice
    -0.73
    ArgsConstructor
    -0.72
    ̍t
    -0.65
     Wikispecies
    -0.65
    DoubleQuotes
    -0.64
    itinéraire
    -0.64
    UpInside
    -0.62
    GOTREF
    -0.61
     ContentValues
    -0.60
    POSITIVE LOGITS
    *)(
    0.46
     voordeel
    0.44
    onFocus
    0.43
    ramo
    0.41
    hematics
    0.41
     racines
    0.40
     évaluation
    0.40
     poil
    0.40
     contribué
    0.40
     Hot
    0.39
    Activations Density 3.343%

    No Known Activations