© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15869
    Prev
    Next
    INDEX
    Explanations

    family or group names

    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_15_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
     📫
    0.62
     ƙ
    0.61
     éd
    0.57
     édition
    0.57
     habitación
    0.57
     chromatographed
    0.56
     жидкости
    0.55
    <unused2152>
    0.54
     партии
    0.54
     *}\
    0.53
    POSITIVE LOGITS
    ’
    0.58
    Ма
    0.56
    <strong>
    0.54
    <code>
    0.53
    <b>
    0.51
    それを
    0.49
     Paral
    0.48
     company
    0.47
    Similar
    0.47
    <i>
    0.47
    Activations Density 0.021%

    No Known Activations