© 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. 4107
    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
    .}$
    2.82
    स
    2.60
    )}$.
    2.47
    EndZ
    2.41
    }$:
    2.33
    ᡧ
    2.33
     dioxide
    2.31
     protobuf
    2.31
    фро
    2.27
    Просе
    2.27
    POSITIVE LOGITS
    the
    2.84
     dotyczą
    2.65
     добиться
    2.55
    てる
    2.34
     ech
    2.33
    व
    2.32
    лася
    2.30
    ρα
    2.29
    esque
    2.28
    tsioon
    2.27
    Activations Density 0.002%

    No Known Activations