© 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. 34985
    Prev
    Next
    INDEX
    Explanations

    mathematical implication symbols and words

    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
    겠
    0.39
    使得
    0.38
     следующее
    0.38
     direct
    0.38
     process
    0.38
     following
    0.38
     następ
    0.38
     troupes
    0.37
     dre
    0.37
     Whatever
    0.37
    POSITIVE LOGITS
    前から
    0.39
     ಮಿಶ್ರ
    0.38
    ension
    0.36
    ention
    0.36
    瞳
    0.36
     যাওয়ার
    0.35
    ेंशन
    0.35
    Coca
    0.35
    }>\
    0.34
     înainte
    0.34
    Activations Density 0.006%

    No Known Activations