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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12649
    Prev
    Next
    INDEX
    Explanations

    words that describe relative position or magnitude, especially in a medical context

    oai_token-act-pair · gemini-2.0-flash

    Medical research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Datuak
    -0.82
     Réponses
    -0.59
    ArgsConstructor
    -0.57
    tagHelperRunner
    -0.56
     ModelExpression
    -0.54
    PropertyChanging
    -0.54
    ControllerAdvice
    -0.54
    وأضاف
    -0.53
    elemField
    -0.52
     supérieures
    -0.52
    POSITIVE LOGITS
    下载附件
    0.57
    finally
    0.52
     Numerade
    0.51
     Paglinawan
    0.48
     finally
    0.47
     OkHttpClient
    0.44
    ngiliz
    0.43
    UnsafeEnabled
    0.43
    glTexCoord
    0.43
    ultima
    0.43
    Activations Density 0.557%

    No Known Activations