© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131142
    Prev
    Next
    INDEX
    Explanations

    doggy style

    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
    \
    0.81
     articolo
    0.74
    <0x0D>
    0.70
    ارة
    0.68
     at
    0.67
    LING
    0.67
    IVE
    0.65
     sanit
    0.63
     burials
    0.63
     raisons
    0.62
    POSITIVE LOGITS
    the
    1.11
    g
    1.10
    thed
    0.97
    their
    0.95
    ك
    0.88
    a
    0.87
    އ
    0.87
    gents
    0.85
    extremely
    0.83
    và
    0.82
    Activations Density 0.000%

    No Known Activations