© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75064
    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_31_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
    opens
    0.40
     exhibits
    0.36
    gp
    0.36
     compound
    0.35
     inhabit
    0.35
     loot
    0.34
    ㅑ
    0.34
    ia
    0.34
     expenditures
    0.33
     General
    0.33
    POSITIVE LOGITS
     largas
    0.44
     minimalistic
    0.40
     விருது
    0.40
    雰
    0.39
     vaginale
    0.39
     partielle
    0.39
     Hilde
    0.39
     کوڈ
    0.38
    தமாக
    0.38
     almeno
    0.38
    Activations Density 0.000%

    No Known Activations