© 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. 124575
    Prev
    Next
    INDEX
    Explanations

    plastic, mechanical, materials, baby, animation, bank, substance, owls, animals

    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
    ي
    0.80
    ка
    0.78
    هي
    0.69
    ی
    0.69
     просты
    0.66
    ﺔ
    0.65
    باس
    0.65
    ת
    0.65
    в
    0.64
    एस
    0.64
    POSITIVE LOGITS
    '
    0.96
    ’
    0.80
    -
    0.76
    _
    0.74
    /
    0.68
    ICK
    0.66
    ARR
    0.66
    BR
    0.63
    GB
    0.63
    的相关
    0.61
    Activations Density 0.001%

    No Known Activations