© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15109
    Prev
    Next
    INDEX
    Explanations

    make a name for

    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_15_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
     harn
    0.64
    㮔
    0.58
     estima
    0.57
     testAvg
    0.57
    )?,
    0.55
     trimestre
    0.54
     보면은
    0.54
     palin
    0.53
     BasicContainer
    0.52
    ㄞ
    0.52
    POSITIVE LOGITS
    overs
    0.52
     opponents
    0.50
     antif
    0.49
    accompl
    0.49
    кати
    0.48
    ירות
    0.48
    av
    0.48
    chemia
    0.48
    activité
    0.47
     surgeons
    0.46
    Activations Density 0.002%

    No Known Activations