© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107227
    Prev
    Next
    INDEX
    Explanations

    speech recognition and classes

    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
    .
    1.59
    ă
    1.15
     steril
    1.11
    ۔
    1.08
    在
    1.07
    ä
    1.02
    ก็
    1.02
    就
    1.02
    是
    1.01
     è
    0.99
    POSITIVE LOGITS
    போது
    1.18
    at
    1.08
    تك
    1.05
    ли
    1.01
    DWARF
    0.93
    ка
    0.92
    اك
    0.92
    ান
    0.92
     lefty
    0.88
    ﺕ
    0.88
    Activations Density 0.038%

    No Known Activations