© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59016
    Prev
    Next
    INDEX
    Explanations

    right

    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_59_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
     straight
    3.25
    Straight
    2.97
    straight
    2.92
     Straight
    2.91
    直
    2.83
     STRAIGHT
    2.59
     thẳng
    2.17
     直
    2.02
     strait
    1.68
     직
    1.56
    POSITIVE LOGITS
     right
    0.70
     Right
    0.70
    Right
    0.68
    right
    0.59
     RIGHT
    0.59
    RIGHT
    0.55
     직접
    0.44
     giusta
    0.43
     右
    0.42
     حق
    0.42
    Activations Density 0.001%

    No Known Activations