© 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. 131296
    Prev
    Next
    INDEX
    Explanations

    Novak Djokovic or Charlize Theron

    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
    </h3>
    1.02
    \
    0.95
    </h2>
    0.92
     WITH
    0.92
     Sesame
    0.83
    </h4>
    0.82
     MARK
    0.81
    டன்
    0.80
    ?
    0.79
     as
    0.79
    POSITIVE LOGITS
    in
    0.97
    는
    0.93
    attacking
    0.82
    2
    0.82
    quarters
    0.81
    irradiation
    0.81
    3
    0.81
    infused
    0.79
    4
    0.79
    اد
    0.78
    Activations Density 0.000%

    No Known Activations