© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105489
    Prev
    Next
    INDEX
    Explanations

    shaped

    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_1_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
    ans
    1.18
    </strong>
    1.16
    </em>
    1.16
    ون
    1.15
    </h3>
    1.13
    in
    1.12
    ih
    1.10
    </h2>
    1.09
    á
    1.03
    í
    1.02
    POSITIVE LOGITS
    ،
    1.24
     energetically
    0.95
    ，
    0.94
     interdependent
    0.93
     emitted
    0.91
     enqueue
    0.89
     unamb
    0.87
     autoload
    0.87
    c
    0.87
    ية
    0.85
    Activations Density 0.000%

    No Known Activations