© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3799
    Prev
    Next
    INDEX
    Explanations

    table comparisons

    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_39_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
    殊
    0.37
    Tracing
    0.36
    hfill
    0.35
    Building
    0.34
     dynam
    0.34
    вершен
    0.34
    សំណ
    0.33
    뾰
    0.33
    csc
    0.33
    㐰
    0.33
    POSITIVE LOGITS
    자리
    0.38
     proportionately
    0.38
     Faroe
    0.38
     hypnotic
    0.37
     homely
    0.36
     hypoallergenic
    0.35
     rebuke
    0.35
     різ
    0.35
     Brotherhood
    0.35
     mesmer
    0.34
    Activations Density 0.003%

    No Known Activations