© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217994
    Prev
    Next
    INDEX
    Explanations

    locations and descriptions

    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_16_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
    wald
    0.56
    ie
    0.52
    sheep
    0.51
    scotch
    0.48
    ác
    0.47
     levels
    0.47
    4
    0.47
    3
    0.46
    u
    0.46
    ć
    0.46
    POSITIVE LOGITS
    চনায়
    0.54
    بلا
    0.50
    ตอน
    0.49
    𝘱
    0.47
    အစိတ်အပိုင်း
    0.47
    लेट
    0.47
    anud
    0.47
    ೇಖ
    0.47
    ikul
    0.46
     kehadiran
    0.46
    Activations Density 0.000%

    No Known Activations