© 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. 162019
    Prev
    Next
    INDEX
    Explanations

    vic or dina

    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
     I
    1.25
    و
    1.08
     It
    1.03
    ad
    0.97
    من
    0.96
    as
    0.93
    ى
    0.92
    c
    0.90
    ار
    0.88
    ך
    0.87
    POSITIVE LOGITS
    он
    1.10
     constitue
    1.10
     preparar
    1.08
     that
    1.05
     dotycz
    1.04
    ↵
    1.03
     decirle
    1.02
     formie
    1.00
     zeigen
    0.97
     retirer
    0.94
    Activations Density 0.001%

    No Known Activations