© 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. 220801
    Prev
    Next
    INDEX
    Explanations

    1950s

    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
     želite
    0.36
    ほしい
    0.35
     प्रकाशन
    0.35
     Meyers
    0.33
    ﯾ
    0.33
     muốn
    0.32
     Where
    0.32
    這個
    0.32
    ská
    0.32
     käs
    0.32
    POSITIVE LOGITS
    嬉
    0.32
     sprang
    0.32
     sprung
    0.31
     enc
    0.31
     support
    0.31
     wholes
    0.30
    नक
    0.30
     lesson
    0.29
     dispensed
    0.29
    แส
    0.29
    Activations Density 0.000%

    No Known Activations