© 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. 43891
    Prev
    Next
    INDEX
    Explanations

    Verb Phrase

    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
    ต
    0.71
    一篇
    0.63
     変
    0.58
     ப்
    0.57
     る
    0.57
    彘
    0.57
     黄
    0.55
    平方
    0.55
    お店
    0.55
    烺
    0.55
    POSITIVE LOGITS
    ।
    0.84
    ী
    0.77
    า
    0.77
    is
    0.75
    s
    0.74
    на
    0.71
    -
    0.71
    ists
    0.71
    ،
    0.71
    ים
    0.70
    Activations Density 0.000%

    No Known Activations