© 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. 88350
    Prev
    Next
    INDEX
    Explanations

    Masaru Kitsuregawa

    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
    ’
    1.29
    '
    1.16
    on
    1.00
    phone
    0.78
    flächen
    0.75
    EVERY
    0.73
    lex
    0.72
    jack
    0.71
    2
    0.71
    ix
    0.71
    POSITIVE LOGITS
     I
    0.87
    ある
    0.85
    م
    0.84
    ই
    0.82
    телю
    0.78
    ری
    0.76
    די
    0.73
    のア
    0.72
    ться
    0.71
    大
    0.71
    Activations Density 0.001%

    No Known Activations