© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35108
    Prev
    Next
    INDEX
    Explanations

    hair styles and lengths

    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_3_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
    ک
    0.71
    श
    0.71
    v
    0.70
    name
    0.69
    質量
    0.68
    ק
    0.66
    も
    0.66
    कोट
    0.65
     اولین
    0.65
    domains
    0.65
    POSITIVE LOGITS
     can
    0.88
     wasn
    0.77
     és
    0.77
    ،
    0.74
     blijft
    0.73
    :
    0.73
     denkt
    0.72
    ي
    0.72
     the
    0.71
     creat
    0.70
    Activations Density 0.005%

    No Known Activations