© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176536
    Prev
    Next
    INDEX
    Explanations

    say "straight"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    जील
    0.40
     commute
    0.34
     voy
    0.33
    ⴷ
    0.33
    玛
    0.33
     horned
    0.32
     commuting
    0.32
     நாள
    0.32
    មា
    0.32
    納
    0.32
    POSITIVE LOGITS
     straight
    1.92
    Straight
    1.88
     Straight
    1.87
    straight
    1.84
     STRAIGHT
    1.66
    直
    1.59
     स्ट्रेट
    1.46
     strait
    1.39
     直
    1.38
     thẳng
    1.37
    Activations Density 0.011%

    No Known Activations