© 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. 108510
    Prev
    Next
    INDEX
    Explanations

    getting into

    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
    ले
    1.06
    ua
    1.04
    い
    1.03
    v
    0.98
    vær
    0.98
    ुर
    0.93
    ens
    0.89
    ją
    0.89
     belieb
    0.88
    ليك
    0.86
    POSITIVE LOGITS
    ’
    1.23
    יר
    1.14
    де
    1.09
    ום
    1.06
    و
    1.05
    ות
    1.05
     but
    1.02
     agit
    1.00
     a
    0.98
    িয়ে
    0.98
    Activations Density 0.000%

    No Known Activations