© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106405
    Prev
    Next
    INDEX
    Explanations

    manic energy, episodes, manicured

    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_1_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
     to
    1.33
    has
    1.31
     has
    1.13
     Has
    1.09
    k
    1.09
     Organiz
    1.08
     Esta
    1.06
     Estad
    1.05
     Interpret
    1.05
     Recomend
    1.04
    POSITIVE LOGITS
    ма
    1.28
    .
    1.01
    с
    1.01
    ↵↵
    0.98
    quele
    0.92
    ел
    0.87
    un
    0.86
    бо
    0.86
    ↵↵↵
    0.85
    ları
    0.84
    Activations Density 0.000%

    No Known Activations