© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117331
    Prev
    Next
    INDEX
    Explanations

    no comments

    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_27_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
    oil
    0.35
    laden
    0.34
    larger
    0.34
    large
    0.33
    ɗ
    0.33
    les
    0.33
     restored
    0.32
     consistently
    0.32
    lev
    0.31
    lez
    0.31
    POSITIVE LOGITS
     Canva
    0.44
     Cash
    0.38
     corris
    0.38
     ट्रोल
    0.37
     Correlations
    0.36
     Anal
    0.35
    㭋
    0.35
     Brain
    0.35
     Sweat
    0.35
     embarazada
    0.35
    Activations Density 0.001%

    No Known Activations