© 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. 75604
    Prev
    Next
    INDEX
    Explanations

    named or named after

    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
     licenses
    0.18
    ṱ
    0.17
     prosperous
    0.16
     lightness
    0.16
    Mou
    0.16
    MotionEvent
    0.16
     palpit
    0.15
     рік
    0.15
     summits
    0.15
    单元
    0.15
    POSITIVE LOGITS
     naming
    0.21
    naming
    0.20
     tibi
    0.20
     धूल
    0.20
    晓
    0.19
     named
    0.18
    äd
    0.18
    Naming
    0.18
     doświad
    0.18
     ugly
    0.17
    Activations Density 0.000%

    No Known Activations