© 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. 125154
    Prev
    Next
    INDEX
    Explanations

    community members

    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
    ab
    0.72
    ND
    0.68
    ↵
    0.66
    ’
    0.66
    on
    0.65
    av
    0.64
    ok
    0.62
     Innen
    0.61
     tatsächlich
    0.61
    ick
    0.60
    POSITIVE LOGITS
    る
    0.89
    စာ
    0.88
    л
    0.86
    いた
    0.86
    на
    0.84
    می
    0.77
    انی
    0.75
    いる
    0.75
     می
    0.73
     a
    0.71
    Activations Density 0.001%

    No Known Activations