© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83326
    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_0_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
    AL
    1.83
    I
    1.80
    ك
    1.63
    The
    1.57
    P
    1.53
    ي
    1.51
    Q
    1.51
    There
    1.50
    4
    1.50
    С
    1.49
    POSITIVE LOGITS
    st
    1.51
    ia
    1.27
    ip
    1.13
    ne
    1.13
    ä
    1.12
    ín
    1.06
    ær
    1.02
    minent
    1.02
    ాన్ని
    1.00
    meler
    0.99
    Activations Density 0.000%

    No Known Activations