© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59338
    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_2_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
    ’
    1.13
    );
    1.09
    ن
    1.06
    n
    1.02
    M
    0.98
    :
    0.93
    U
    0.93
    C
    0.92
     it
    0.89
     do
    0.87
    POSITIVE LOGITS
    л
    1.82
    ل
    1.65
    at
    1.53
    u
    1.34
    лло
    1.31
    ро
    1.27
    ल
    1.23
    т
    1.18
    ル
    1.11
    на
    1.09
    Activations Density 0.000%

    No Known Activations