© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138214
    Prev
    Next
    INDEX
    Explanations

    wants or warrants after user/author

    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_12_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
    ن
    0.59
    𝘸
    0.58
    jeli
    0.54
    ܓ
    0.54
    f
    0.52
    মেন্ট
    0.52
    a
    0.52
    omez
    0.51
    לים
    0.51
    UISE
    0.51
    POSITIVE LOGITS
    ’,
    0.59
    ’)
    0.57
    )，
    0.53
    )
    0.53
    ः
    0.52
    rapped
    0.52
    ۲۰
    0.51
    2
    0.50
    ’),
    0.50
    łącznie
    0.50
    Activations Density 0.000%

    No Known Activations