© 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. 216280
    Prev
    Next
    INDEX
    Explanations

    better exchange rate

    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
     시행
    0.44
    normal
    0.40
     běž
    0.40
     sebebi
    0.39
     செயல்படுத்த
    0.39
     aufgrund
    0.38
    බ
    0.37
    ૬
    0.36
     upang
    0.36
    હીં
    0.35
    POSITIVE LOGITS
     Commit
    0.44
     commit
    0.43
     commits
    0.42
     access
    0.41
     image
    0.41
     Image
    0.41
     advocates
    0.41
     optimizes
    0.40
     handles
    0.39
     file
    0.39
    Activations Density 0.000%

    No Known Activations