© 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. 228227
    Prev
    Next
    INDEX
    Explanations

    typescript code

    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
     it
    1.21
    će
    1.09
    ı
    1.06
    ert
    1.05
    ได้
    1.05
    O
    1.05
    c
    1.02
     el
    1.02
     be
    1.01
    ong
    1.01
    POSITIVE LOGITS
    н
    1.21
    ються
    1.00
    ޏ
    1.00
    اک
    0.97
    터
    0.93
    г
    0.92
    ю
    0.91
    OLYBD
    0.89
    беріга
    0.89
    аз
    0.88
    Activations Density 0.003%

    No Known Activations