© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141786
    Prev
    Next
    INDEX
    Explanations

    Pocket

    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_0_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
    い
    2.20
    л
    1.96
    на
    1.69
    ר
    1.67
    0
    1.63
    り
    1.59
    ある
    1.55
    ون
    1.53
    ii
    1.52
    ८
    1.52
    POSITIVE LOGITS
    1.80
    y
    1.37
    </h6>
    1.28
    </th>
    1.22
    erv
    1.20
    </h3>
    1.20
    urp
    1.17
    is
    1.14
    urine
    1.13
    urr
    1.12
    Activations Density 0.000%

    No Known Activations