© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124118
    Prev
    Next
    INDEX
    Explanations

    names and urban origins

    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
    ۔
    0.78
    </strong>
    0.77
    ;
    0.77
    -
    0.74
    s
    0.73
    이었다
    0.72
    －
    0.72
    /
    0.71
    >
    0.71
    ні
    0.69
    POSITIVE LOGITS
    ệt
    0.64
     Союза
    0.61
     inscre
    0.60
    emies
    0.58
    য়া
    0.58
    íamos
    0.57
    ложений
    0.57
    ooka
    0.57
    ovania
    0.57
    ந்தைய
    0.57
    Activations Density 0.000%

    No Known Activations