© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 168178
    Prev
    Next
    INDEX
    Explanations

    small chickenpox

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     mos
    0.39
     recus
    0.37
     eslint
    0.36
    ォ
    0.36
    শিপ
    0.34
    arker
    0.33
    UNKNOWN
    0.33
     covid
    0.33
     francis
    0.32
     swallow
    0.32
    POSITIVE LOGITS
     P
    0.68
     Small
    0.65
     small
    0.64
    П
    0.62
     П
    0.61
    small
    0.61
    Small
    0.60
     pequeña
    0.59
    P
    0.58
     piccole
    0.56
    Activations Density 0.000%

    No Known Activations