© 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-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171053
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ആരോപ
    0.44
     Sought
    0.39
    ශ
    0.39
     coût
    0.37
    φή
    0.37
     poté
    0.37
    瞍
    0.36
    忓
    0.36
     gauche
    0.36
    সাম্প্র
    0.36
    POSITIVE LOGITS
    akit
    0.36
    azing
    0.35
    isieren
    0.35
    ags
    0.33
    umela
    0.33
    <s>
    0.33
    isierung
    0.33
    ansas
    0.33
     वैरिएंट
    0.33
    WWE
    0.33
    Activations Density 0.000%

    No Known Activations