© 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. 111910
    Prev
    Next
    INDEX
    Explanations

    sencillo / sencilla

    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
    t
    1.57
    人
    1.48
    ang
    1.45
    大
    1.36
    ن
    1.32
    ها
    1.25
    ン
    1.24
    al
    1.20
    in
    1.16
    ار
    1.13
    POSITIVE LOGITS
     desenvolv
    1.17
     produz
    1.16
     a
    1.15
     analiz
    1.08
     falar
    1.05
     използва
    1.04
    H
    1.03
     pregunt
    1.02
     kaynak
    1.02
     lojas
    1.01
    Activations Density 0.000%

    No Known Activations