© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83954
    Prev
    Next
    INDEX
    Explanations

    comprehension

    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_0_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
    ли
    1.58
    aan
    1.34
    es
    1.30
    ס
    1.30
    d
    1.25
    s
    1.23
    ot
    1.20
    inci
    1.19
    á
    1.18
    averaged
    1.17
    POSITIVE LOGITS
    н
    1.83
    ك
    1.80
    ン
    1.72
    م
    1.54
    ка
    1.53
    ุ
    1.52
    м
    1.41
     exclu
    1.40
    ل
    1.33
    к
    1.33
    Activations Density 0.001%

    No Known Activations