© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175281
    Prev
    Next
    INDEX
    Explanations

    event

    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_20_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
     ll
    0.39
     polymeric
    0.35
    ķ
    0.35
     devem
    0.35
     flaps
    0.35
    emas
    0.35
    compart
    0.34
    jacoco
    0.34
     enzimas
    0.33
     حیثیت
    0.33
    POSITIVE LOGITS
    Faith
    0.40
    Community
    0.37
    $-$
    0.37
     returned
    0.37
    Town
    0.37
    Orlando
    0.37
    Freight
    0.36
    Cra
    0.35
    Target
    0.34
     하나님의
    0.34
    Activations Density 0.000%

    No Known Activations