© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88929
    Prev
    Next
    INDEX
    Explanations

    here

    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
    p
    0.74
    s
    0.71
    Present
    0.68
    bereit
    0.65
    t
    0.65
    present
    0.64
     Bás
    0.62
     Owls
    0.61
    in
    0.59
    ig
    0.58
    POSITIVE LOGITS
    на
    1.01
    то
    0.88
    िया
    0.77
    ла
    0.74
    р
    0.68
    ро
    0.68
    ㅋㅋㅋㅋ
    0.67
    なっている
    0.67
    ний
    0.66
     миллиар
    0.66
    Activations Density 0.001%

    No Known Activations