© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227225
    Prev
    Next
    INDEX
    Explanations

    rajl, tdir

    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>
    1.12
     the
    0.92
    </h1>
    0.89
    </h6>
    0.89
    nn
    0.88
     be
    0.88
    </h4>
    0.81
    </sub>
    0.81
     da
    0.80
     o
    0.80
    POSITIVE LOGITS
    ين
    1.37
    ра
    1.19
    ور
    1.18
    оне
    1.02
    ат
    1.00
    ор
    0.94
    ет
    0.93
    اب
    0.92
    ુ
    0.89
    ар
    0.88
    Activations Density 0.003%

    No Known Activations