© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234512
    Prev
    Next
    INDEX
    Explanations

    Where

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    历史
    0.41
    BAN
    0.39
     прось
    0.38
    ڈین
    0.38
    댄
    0.37
    Yon
    0.37
    馔
    0.37
    쥘
    0.37
    ANGO
    0.37
    热
    0.37
    POSITIVE LOGITS
     kommen
    0.48
     come
    0.45
     kommer
    0.45
     Comes
    0.42
    ிகளில்
    0.42
     viennent
    0.42
     came
    0.41
     আসছেন
    0.41
     COME
    0.41
    Come
    0.41
    Activations Density 0.003%

    No Known Activations