© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 44655
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    BUGFS
    0.70
    neş
    0.64
    BuildContext
    0.63
    ریشن
    0.63
    ل
    0.61
     divaricatis
    0.60
     ویژگی
    0.59
    یشہ
    0.59
    I
    0.59
     σαν
    0.58
    POSITIVE LOGITS
     for
    0.90
    5
    0.80
     durch
    0.75
     )
    0.74
    7
    0.72
    of
    0.71
    4
    0.71
     in
    0.71
    for
    0.66
    6
    0.66
    Activations Density 0.001%

    No Known Activations