© 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. 43814
    Prev
    Next
    INDEX
    Explanations

    Eric (names/authors/places)

    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
    是
    0.66
    不
    0.63
    ла
    0.62
     deaktiv
    0.62
    ing
    0.60
    ed
    0.59
    ছিল
    0.59
    有没有
    0.58
    是真的
    0.58
    enar
    0.57
    POSITIVE LOGITS
    ната
    0.60
    нда
    0.58
    нах
    0.58
    αι
    0.57
    q
    0.57
    стати
    0.57
    .
    0.56
    ृत
    0.54
    )",
    0.53
    .".
    0.53
    Activations Density 0.008%

    No Known Activations