© 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. 35877
    Prev
    Next
    INDEX
    Explanations

    conditional 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
    ୧
    0.21
     фи
    0.18
     مح
    0.18
    漬
    0.17
    Fus
    0.17
    लीज
    0.17
    ریح
    0.16
    廨
    0.16
     جز
    0.16
    葙
    0.16
    POSITIVE LOGITS
    parameters
    0.20
    teger
    0.19
    estamps
    0.19
    numerator
    0.19
    matches
    0.18
    emples
    0.18
     incógn
    0.18
    variables
    0.18
    ers
    0.17
     posterity
    0.17
    Activations Density 0.005%

    No Known Activations