© 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. 211241
    Prev
    Next
    INDEX
    Explanations

    erfurt, Gotha, Thuringia

    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_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
    p
    1.16
     of
    1.09
    يس
    1.06
     on
    1.05
    يد
    1.04
    ння
    0.95
    ле
    0.94
    t
    0.93
    يه
    0.93
    সময়
    0.93
    POSITIVE LOGITS
    م
    1.29
    1.28
    س
    1.27
    ا
    1.16
    ন
    1.03
    !
    1.02
    em
    0.97
    ।
    0.96
    ু
    0.96
    <h4>
    0.96
    Activations Density 0.000%

    No Known Activations