© 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
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132599
    Prev
    Next
    INDEX
    Explanations

    boobs

    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_6_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
     quince
    0.79
     yakin
    0.79
     columnalign
    0.78
     boli
    0.78
    ’
    0.77
    이다
    0.75
     discer
    0.73
     blockchain
    0.73
    ),
    0.73
     benefic
    0.72
    POSITIVE LOGITS
    et
    1.51
    h
    1.47
    ik
    1.38
    ir
    1.36
    ia
    1.31
    ن
    1.27
    ab
    1.26
    ন
    1.25
    ag
    1.20
    n
    1.17
    Activations Density 0.000%

    No Known Activations