© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211227
    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_5_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
    1.20
    ↵
    1.15
     arrogance
    0.98
    ↵↵
    0.98
     agreg
    0.92
     operar
    0.91
     comercio
    0.90
     "");
    0.89
     আম
    0.89
    াহ
    0.89
    POSITIVE LOGITS
    is
    1.65
    the
    1.64
    o
    1.48
    л
    1.41
    as
    1.41
    ad
    1.40
    A
    1.31
    í
    1.28
    ing
    1.27
    é
    1.27
    Activations Density 0.000%

    No Known Activations