© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134483
    Prev
    Next
    INDEX
    Explanations

    software packages

    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_1_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
     for
    1.38
     be
    1.30
    ם
    1.26
    ش
    1.23
    기
    1.19
    in
    1.18
    ing
    1.13
    ين
    1.12
    ن
    1.09
     to
    1.05
    POSITIVE LOGITS
     یا
    0.95
    に向けて
    0.90
    ९
    0.89
     सांगितले
    0.85
    AT
    0.83
    ма
    0.83
     এরই
    0.83
    нын
    0.80
    funktionen
    0.79
    }$,
    0.78
    Activations Density 0.001%

    No Known Activations