© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57003
    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_11_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
     have
    0.65
     that
    0.55
     are
    0.53
     were
    0.53
     è
    0.50
    我们
    0.49
     I
    0.49
    เป็น
    0.48
    ò
    0.48
     motion
    0.48
    POSITIVE LOGITS
    reporting
    0.50
     Tattha
    0.47
    camel
    0.47
     REGIUNI
    0.45
    ገድ
    0.45
     барои
    0.44
    ClrBit
    0.44
    рга
    0.44
    bron
    0.44
    ٻ
    0.43
    Activations Density 0.000%

    No Known Activations