© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6576
    Prev
    Next
    INDEX
    Explanations

    qualifying adjectives

    oai_token-act-pair · gemini-2.0-flash

    many

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    many
    -0.79
     Many
    -0.75
     many
    -0.73
    Many
    -0.71
     Numerous
    -0.65
     múltiples
    -0.65
    Numerous
    -0.61
     MANY
    -0.60
     várias
    -0.59
     nombreuses
    -0.59
    POSITIVE LOGITS
    protoimpl
    0.75
    LookAnd
    0.73
     ویکی‌پدی
    0.71
    InjectAttribute
    0.68
    IsContent
    0.66
    +#+
    0.66
     resourceCulture
    0.65
    oredCriteria
    0.65
     IERC
    0.63
    JpaRepository
    0.63
    Activations Density 2.156%

    No Known Activations