© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143291
    Prev
    Next
    INDEX
    Explanations

    adapt

    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_0_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
    k
    1.50
    ם
    1.43
    ك
    1.42
    ro
    1.38
    ons
    1.38
    ir
    1.34
    z
    1.28
    ER
    1.27
    a
    1.27
    it
    1.26
    POSITIVE LOGITS
    К
    1.45
     synthes
    1.27
     powied
    1.21
    Е
    1.15
     prennent
    1.13
    نی
    1.10
    З
    1.10
    ни
    1.09
     encontrar
    1.09
    を利用
    1.07
    Activations Density 0.001%

    No Known Activations