© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167249
    Prev
    Next
    INDEX
    Explanations

    operators and comparisons

    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
    
    0.37
    Ends
    0.35
    ARROW
    0.34
     került
    0.33
    ξει
    0.33
    都不
    0.33
     kerül
    0.33
    否
    0.33
     इक्वेशन
    0.33
    残念
    0.33
    POSITIVE LOGITS
     χω
    0.36
     veril
    0.36
    ៈ
    0.35
     conversion
    0.35
     Prestige
    0.35
    Glide
    0.35
    用地
    0.34
    abeth
    0.34
     mouse
    0.34
     dxe
    0.33
    Activations Density 0.001%

    No Known Activations