© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8911
    Prev
    Next
    INDEX
    Explanations

    percentages, measurements, and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يا
    3.06
    𝘭
    2.65
    й
    2.43
     erst
    2.42
     placés
    2.39
    ভাগ
    2.35
    ма
    2.34
    व
    2.34
     quelles
    2.32
    ্নে
    2.29
    POSITIVE LOGITS
    cription
    2.95
    ा
    2.76
    ių
    2.73
     turbidity
    2.63
     kinetics
    2.50
     acetic
    2.48
    ᐈ
    2.46
    nte
    2.42
    ফ
    2.40
    tering
    2.38
    Activations Density 0.051%

    No Known Activations