© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77859
    Prev
    Next
    INDEX
    Explanations

    keys followed by colon

    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_31_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
    etown
    0.39
    Nz
    0.39
     मच्छर
    0.38
     μπορού
    0.37
    淝
    0.37
    重視
    0.37
     Nz
    0.37
    /";
    0.36
    olf
    0.36
     क्यों
    0.36
    POSITIVE LOGITS
    算
    0.44
     blanco
    0.39
    𝚜
    0.37
    对接
    0.37
    支部
    0.37
     dajj
    0.37
     சிறு
    0.36
    AddModelError
    0.36
     ,
    0.36
     شبکه
    0.36
    Activations Density 0.001%

    No Known Activations