© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13947
    Prev
    Next
    INDEX
    Explanations

    words related to humor, opinions, and writing styles, especially in informal contexts.

    oai_token-act-pair · gemini-2.0-flash

    code identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     विश्वसनीयता
    -0.59
    ganu
    -0.54
    Życiorys
    -0.54
     lande
    -0.53
     Normdatei
    -0.53
    pinas
    -0.52
     ActionResult
    -0.52
    braio
    -0.52
     nahilalakip
    -0.52
     ostavi
    -0.51
    POSITIVE LOGITS
    migrationBuilder
    0.72
    ConstraintMaker
    0.64
     cor
    0.60
     CreateTagHelper
    0.60
    awtextra
    0.56
     original
    0.50
     "..\..\..\
    0.49
     Original
    0.47
    IntoConstraints
    0.46
    Seeder
    0.45
    Activations Density 4.181%

    No Known Activations