© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45051
    Prev
    Next
    INDEX
    Explanations

    redux store creation

    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_22_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
     slightest
    0.45
     intense
    0.44
     확인할
    0.43
    іб
    0.42
     ferocious
    0.41
     concerted
    0.41
     subtlet
    0.40
    ༈
    0.40
     subtleties
    0.40
    鸦
    0.40
    POSITIVE LOGITS
    Ë
    0.40
    men
    0.38
    arriv
    0.38
    mann
    0.37
    ugi
    0.36
    ermann
    0.35
    pev
    0.35
    Стра
    0.35
    ami
    0.35
    equ
    0.34
    Activations Density 0.000%

    No Known Activations