© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201399
    Prev
    Next
    INDEX
    Explanations

    om, o, an, bt, og

    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
    z
    0.71
    c
    0.64
    ";
    0.55
    ia
    0.55
     ज्वाइन
    0.54
    кха
    0.54
    d
    0.53
    OnFileChange
    0.52
    .*
    0.52
    baren
    0.52
    POSITIVE LOGITS
    ย
    0.72
    ｙ
    0.70
    е
    0.69
    ９
    0.68
    ８
    0.66
    ್ರ
    0.63
    ので
    0.62
    ки
    0.61
    การ
    0.61
    ้
    0.61
    Activations Density 0.000%

    No Known Activations