© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121988
    Prev
    Next
    INDEX
    Explanations

    detailed description

    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_3_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
    t
    0.67
    e
    0.61
    ﻪ
    0.57
    ﻚ
    0.57
    n
    0.56
    l
    0.55
    蛯
    0.55
    an
    0.54
     deliberately
    0.54
    doesn
    0.54
    POSITIVE LOGITS
     to
    0.96
     of
    0.74
    ？
    0.67
    ↵↵
    0.66
     usuarios
    0.66
    )。
    0.66
    ме
    0.65
     from
    0.63
     publicités
    0.63
    ă
    0.63
    Activations Density 0.002%

    No Known Activations