© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9994
    Prev
    Next
    INDEX
    Explanations

    cheekbones and jawline

    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_13_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
    )
    0.48
     affinities
    0.46
     baloncesto
    0.46
    )\
    0.46
    ன
    0.45
    смотре
    0.45
    ুস
    0.44
     penchant
    0.44
     academies
    0.44
     arteries
    0.44
    POSITIVE LOGITS
    s
    0.46
    cY
    0.46
    হত
    0.45
    lng
    0.44
    ಿಯಾಗ
    0.44
    ोरेशन
    0.43
    ARDS
    0.42
    zysz
    0.42
    crim
    0.41
    يس
    0.40
    Activations Density 0.012%

    No Known Activations