© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40040
    Prev
    Next
    INDEX
    Explanations

    tank

    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_57_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
    زمت
    0.42
    storage
    0.40
     storage
    0.39
    żyt
    0.39
     রাহ
    0.39
    ﷻ
    0.38
     armazenamento
    0.37
    Iranian
    0.37
     almacenamiento
    0.37
    ):=\
    0.36
    POSITIVE LOGITS
     tank
    0.96
    Tank
    0.91
     Tank
    0.87
     tanks
    0.86
    tank
    0.81
     Tanks
    0.79
    TANK
    0.78
    탱
    0.70
     टैंक
    0.70
     tanque
    0.70
    Activations Density 0.023%

    No Known Activations