© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46141
    Prev
    Next
    INDEX
    Explanations

    Proven track record, corrosion rates, muscle tension

    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_13_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
    жными
    0.55
    ล
    0.55
    шь
    0.54
    зь
    0.51
    льним
    0.51
    ין
    0.49
    らない
    0.49
    豢
    0.47
    жных
    0.47
     इन
    0.46
    POSITIVE LOGITS
     pracuje
    0.49
     dañ
    0.48
     blowout
    0.47
    en
    0.47
     coupé
    0.47
     pá
    0.47
     todavía
    0.47
     behö
    0.46
     nonché
    0.45
     méd
    0.45
    Activations Density 0.000%

    No Known Activations