© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9481
    Prev
    Next
    INDEX
    Explanations

    the word "framework," and possibly things that are hosted on Github

    oai_token-act-pair · gemini-2.0-flash

    framework

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    arella
    -0.63
     følger
    -0.60
    UAGE
    -0.60
     nélk
    -0.59
    broek
    -0.59
    botella
    -0.58
    vermögen
    -0.58
    werpen
    -0.57
    selben
    -0.57
     waard
    -0.57
    POSITIVE LOGITS
    GEBURTSDATUM
    1.21
    LookAnd
    1.17
     nakalista
    1.16
    parsedMessage
    1.12
    migrationBuilder
    1.05
    sizeCache
    1.03
    __':
    1.03
     resourceCulture
    1.02
    KommentareTeilen
    1.01
    UnusedPrivate
    1.01
    Activations Density 0.284%

    No Known Activations