© 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. 161793
    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
    :
    1.33
    >
    1.16
    AN
    1.06
    iz
    1.03
    THAT
    0.99
    AL
    0.98
    AS
    0.96
    AR
    0.93
    STEIN
    0.92
    IS
    0.91
    POSITIVE LOGITS
    ли
    1.87
    ק
    1.41
    اب
    1.40
    ها
    1.36
    人
    1.23
    ει
    1.23
    я
    1.20
    ے
    1.19
    ווי
    1.17
    ет
    1.15
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.