© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13727
    Prev
    Next
    INDEX
    Explanations

    words related to data storage and representation, also capturing some medical and legal jargon

    oai_token-act-pair · gemini-2.0-flash

    "ent" and "ence" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ment
    -0.75
    ant
    -0.65
    ments
    -0.63
    ⓧ
    -0.62
    MENT
    -0.60
     للاسماء
    -0.58
    ement
    -0.57
    XmlEnum
    -0.56
    ants
    -0.54
    ApiProperty
    -0.54
    POSITIVE LOGITS
    ViewImports
    0.74
    en
    0.59
     commerciali
    0.55
    ENS
    0.53
    IVAS
    0.53
    ens
    0.52
     soumis
    0.52
    PreferredItem
    0.52
     européennes
    0.51
    єн
    0.51
    Activations Density 5.846%

    No Known Activations