© 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. 50316
    Prev
    Next
    INDEX
    Explanations

    specific word or token following

    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
     brackets
    0.34
     appearing
    0.33
     adher
    0.33
     pliable
    0.33
     italics
    0.32
     catal
    0.32
     parenthesis
    0.32
    闢
    0.32
     adhering
    0.32
     sublattice
    0.31
    POSITIVE LOGITS
    钏
    0.34
     Specifies
    0.33
    ḩ
    0.33
    恈
    0.33
    сси
    0.33
     làn
    0.32
     Isometric
    0.32
    遌
    0.32
     Honorary
    0.32
     ঠে
    0.32
    Activations Density 0.000%

    No Known Activations