© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34725
    Prev
    Next
    INDEX
    Explanations

    hat, cap, or headwear

    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_31_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
    烃
    0.38
    ikes
    0.37
    nię
    0.37
    alcool
    0.36
     Mehr
    0.36
    expérience
    0.35
    anthrop
    0.35
     раство
    0.34
     établissement
    0.34
     alkohol
    0.34
    POSITIVE LOGITS
     hat
    0.68
     hats
    0.65
    帽
    0.63
    帽子
    0.61
     intracranial
    0.60
     cap
    0.59
    👒
    0.58
     Hat
    0.55
    Hat
    0.51
     head
    0.50
    Activations Density 0.021%

    No Known Activations