© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3380
    Prev
    Next
    INDEX
    Explanations

    mentions of measurements and mandatory activities

    oai_token-act-pair · gemini-2.0-flash

    hours/data storage size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    webElementXpaths
    -0.56
     zun
    -0.48
    owol
    -0.48
    각주
    -0.48
     Bestimmung
    -0.47
     bis
    -0.45
    ])[
    -0.43
    ത്
    -0.42
    クレ
    -0.42
    })`
    -0.41
    POSITIVE LOGITS
     propOrder
    0.69
     tslint
    0.68
    AndEndTag
    0.62
     NotImplemented
    0.59
    лтамалар
    0.55
     pernah
    0.55
    PreAuthorize
    0.54
    DropTable
    0.54
    lägen
    0.54
    Eloquent
    0.54
    Activations Density 3.370%

    No Known Activations