© 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. 33396
    Prev
    Next
    INDEX
    Explanations

    LexFortis, GeeksforGeeks, GeeksQuiz

    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
     ইহাতে
    0.38
     Greenfield
    0.34
     Spaghetti
    0.33
    <tfoot>
    0.33
    calculator
    0.33
    empty
    0.32
     रखती
    0.32
    WU
    0.31
    xlsx
    0.31
    %"},
    0.31
    POSITIVE LOGITS
     Madhya
    0.43
     hormone
    0.43
     Janata
    0.41
     hormones
    0.41
     Andhra
    0.40
     aspirant
    0.40
     CBSE
    0.40
     aspirants
    0.40
     BJP
    0.40
     côtes
    0.39
    Activations Density 0.000%

    No Known Activations