© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137656
    Prev
    Next
    INDEX
    Explanations

    ,

    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_37_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
    צל
    0.42
    workshop
    0.38
    cF
    0.37
    cery
    0.37
    wach
    0.36
    届
    0.36
    ামূলক
    0.35
    thy
    0.35
    brake
    0.34
    alogical
    0.34
    POSITIVE LOGITS
     chewing
    1.31
     gum
    1.20
     Gum
    1.10
     chewed
    1.06
    Gum
    1.05
     chew
    1.03
    gum
    0.95
    껌
    0.85
     gums
    0.84
     Chew
    0.79
    Activations Density 0.001%

    No Known Activations