© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4017
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    হাম্মদ
    0.69
    ка
    0.66
     vague
    0.65
    siniz
    0.64
     fist
    0.63
    вання
    0.63
    ﻲ
    0.63
    ্লিকেশন
    0.63
    executor
    0.60
    ant
    0.59
    POSITIVE LOGITS
     Gelegenheit
    0.63
    ش
    0.62
    i
    0.62
    aula
    0.58
    u
    0.56
    лень
    0.53
     supremacy
    0.52
    에는
    0.52
    цю
    0.52
    ど
    0.52
    Activations Density 0.000%

    No Known Activations