© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15286
    Prev
    Next
    INDEX
    Explanations

    dates and references to legal and political bodies

    oai_token-act-pair · gemini-2.0-flash

    Official actions and decisions

    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
     NSCoder
    -0.73
    évaluateur
    -0.55
     pledge
    -0.54
    ModelAdmin
    -0.54
    interopRequire
    -0.52
    ại
    -0.50
     AppColors
    -0.49
     UIAlert
    -0.49
     Pact
    -0.49
     flake
    -0.48
    POSITIVE LOGITS
    migrationBuilder
    0.56
    __":
    0.56
    __':
    0.54
    ContentAsync
    0.53
    atorship
    0.52
    usercontent
    0.52
    :][
    0.52
     насељу
    0.52
    ISupport
    0.49
    IUrlHelper
    0.49
    Activations Density 2.234%

    No Known Activations