© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134874
    Prev
    Next
    INDEX
    Explanations

    incel

    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_6_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
    ک
    1.17
    ی
    1.06
    на
    1.05
    ку
    1.02
     İran
    1.00
    سی
    0.96
    দ
    0.95
    ের
    0.94
    לי
    0.92
    종
    0.92
    POSITIVE LOGITS
    ed
    1.27
    as
    1.12
    at
    1.11
    el
    1.10
    ant
    1.01
    ar
    0.99
    en
    0.96
    og
    0.96
    al
    0.95
    o
    0.93
    Activations Density 0.002%

    No Known Activations