© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66456
    Prev
    Next
    INDEX
    Explanations

    compass, calipers, dividers, Golden Ratio

    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_41_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
    ဋ
    0.43
    Cas
    0.40
    萄
    0.39
     GW
    0.39
     CAS
    0.38
     Derbyshire
    0.38
     WS
    0.38
    }]_{
    0.37
     Watanabe
    0.37
     ಅಮ
    0.36
    POSITIVE LOGITS
     compass
    1.09
     slide
    0.97
    Compass
    0.96
     Compass
    0.93
    compass
    0.90
    slide
    0.88
     Slide
    0.84
    Slide
    0.82
     calipers
    0.81
     dividers
    0.75
    Activations Density 0.020%

    No Known Activations