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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11508
    Prev
    Next
    INDEX
    Explanations

    language found in briefs, depositions and court orders.

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    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
    Compat
    -0.52
    endwhile
    -0.47
    OrBuilder
    -0.47
     thereto
    -0.45
    ണ്
    -0.45
    basicConfig
    -0.44
     whereof
    -0.44
    HomeAsUpEnabled
    -0.44
     dazu
    -0.44
    complexContent
    -0.44
    POSITIVE LOGITS
     transfieras
    0.68
    queryInterface
    0.63
    kháu
    0.60
     challenged
    0.59
    typeorm
    0.57
    mybatisplus
    0.57
    +#+
    0.56
     Audiodateien
    0.56
    rå
    0.56
    רץ
    0.54
    Activations Density 6.467%

    No Known Activations