© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198575
    Prev
    Next
    INDEX
    Explanations

    Give name to something

    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
     immediately
    0.42
     importantes
    0.40
     immédiatement
    0.40
     swath
    0.38
     inmediatamente
    0.38
    露出
    0.38
     hyster
    0.38
    <unused1097>
    0.37
     رحمت
    0.37
     gent
    0.37
    POSITIVE LOGITS
    process
    0.41
    GameObject
    0.41
    upt
    0.38
    since
    0.38
     nemmeno
    0.38
    Education
    0.38
    ng
    0.36
    inhos
    0.36
    सह
    0.36
    قط
    0.36
    Activations Density 0.002%

    No Known Activations