© 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. 157244
    Prev
    Next
    INDEX
    Explanations

    ian or ial followed by ion

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ۹
    1.13
    á
    1.13
    üm
    1.04
    4
    1.00
    9
    0.99
     când
    0.98
    :
    0.97
     was
    0.94
    ني
    0.94
     ."
    0.93
    POSITIVE LOGITS
    to
    1.21
    '
    1.18
    ch
    1.01
    های
    0.99
    不
    0.98
    好
    0.96
    of
    0.95
    सी
    0.92
    ﺍ
    0.92
    ست
    0.91
    Activations Density 0.000%

    No Known Activations