© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91224
    Prev
    Next
    INDEX
    Explanations

    al

    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_3_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
    ের
    0.94
    на
    0.88
    </h2>
    0.87
    </h3>
    0.86
    </h4>
    0.80
    ின்
    0.73
    </sub>
    0.72
    </h5>
    0.69
    </b>
    0.65
    t
    0.64
    POSITIVE LOGITS
    i
    0.73
    A
    0.70
    M
    0.68
    rie
    0.67
    Sing
    0.66
    om
    0.66
    j
    0.66
    urangan
    0.65
    ：
    0.64
     singles
    0.64
    Activations Density 0.004%

    No Known Activations