© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163537
    Prev
    Next
    INDEX
    Explanations

    bowl, dip, and honey

    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
     заклад
    0.46
    配達
    0.39
     Lieferung
    0.38
     Snow
    0.36
    涔
    0.36
    Snow
    0.36
     VF
    0.35
     Wit
    0.35
     Ludwig
    0.35
     sled
    0.35
    POSITIVE LOGITS
    isure
    0.40
     ಅ
    0.38
     marinas
    0.38
     present
    0.36
     Press
    0.36
     interstitial
    0.36
     gossip
    0.36
     routing
    0.36
     كويس
    0.35
    ouin
    0.35
    Activations Density 0.034%

    No Known Activations