© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261500
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     instituted
    0.47
    ি
    0.44
    CONSTRAINT
    0.44
    θούν
    0.43
    드
    0.43
    од
    0.42
    葢
    0.42
     दौरान
    0.42
     REQUIRE
    0.42
    托
    0.41
    POSITIVE LOGITS
    Teams
    0.53
    team
    0.53
     amplitude
    0.53
    nutrient
    0.52
     millennials
    0.50
    mile
    0.49
    tech
    0.49
    valve
    0.49
    market
    0.48
    partners
    0.48
    Activations Density 0.000%

    No Known Activations