© 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. 153374
    Prev
    Next
    INDEX
    Explanations

    leave this blank

    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
    oliath
    0.43
     //!
    0.40
     Manning
    0.39
    }^{*},
    0.39
    桓
    0.39
    anation
    0.38
     características
    0.38
    nicki
    0.38
     nä
    0.38
     olio
    0.38
    POSITIVE LOGITS
     těch
    0.44
    콩
    0.44
     phê
    0.43
     моих
    0.43
    醅
    0.42
     그
    0.42
    рел
    0.42
     영상
    0.41
     videot
    0.40
     वीडियो
    0.40
    Activations Density 0.000%

    No Known Activations