© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18619
    Prev
    Next
    INDEX
    Explanations

    percentage of

    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_34_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
     majority
    0.48
    majority
    0.47
     Majority
    0.45
    Majority
    0.45
     \"%
    0.42
     fractions
    0.42
     اکثریت
    0.41
    /%
    0.41
     полови
    0.40
     अधिकांश
    0.40
    POSITIVE LOGITS
     PROFITS
    0.35
     ماحول
    0.35
    fts
    0.34
    ishes
    0.34
     respondents
    0.33
    有时
    0.33
     সামগ্র
    0.32
     totales
    0.31
     निश्चित
    0.31
     undergraduates
    0.31
    Activations Density 0.007%

    No Known Activations