© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150014
    Prev
    Next
    INDEX
    Explanations

    button click or key press

    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_23_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
    myCollision
    0.45
    ッティング
    0.43
    Ұ
    0.39
    Capable
    0.39
    мили
    0.39
    בול
    0.38
    廷
    0.38
    ὴν
    0.38
    𝒇
    0.37
    遨
    0.36
    POSITIVE LOGITS
     pandémie
    0.47
     kulturn
    0.44
     decode
    0.43
     wielu
    0.41
     transform
    0.41
     pione
    0.39
    ikken
    0.39
     culture
    0.38
     kolem
    0.38
     decoder
    0.38
    Activations Density 0.001%

    No Known Activations