© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201170
    Prev
    Next
    INDEX
    Explanations

    car brands and models

    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_12_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
    य़ा
    0.57
    ⿶
    0.57
    ̀u
    0.56
     ทํา
    0.55
    粹
    0.55
    graphHead
    0.52
    Ꭴ
    0.52
    ťou
    0.51
     සෑම
    0.51
     ү
    0.51
    POSITIVE LOGITS
    ロ
    0.57
    ANOVA
    0.55
    一
    0.52
    is
    0.51
     puri
    0.49
    OS
    0.49
    Pro
    0.49
    Disposable
    0.48
    Panoramic
    0.47
    Kend
    0.47
    Activations Density 0.000%

    No Known Activations