© 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. 42419
    Prev
    Next
    INDEX
    Explanations

    runestone service alphabet

    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
    ت
    0.87
    दी
    0.82
    ри
    0.79
    ीय
    0.75
    تها
    0.70
    تان
    0.70
    त्रि
    0.70
    dans
    0.67
    تن
    0.67
    መም
    0.67
    POSITIVE LOGITS
     be
    0.88
     not
    0.71
    8
    0.68
    0
    0.68
    <0x80>
    0.67
     /
    0.66
    zelf
    0.64
    ist
    0.61
    ști
    0.61
    </td>
    0.58
    Activations Density 0.009%

    No Known Activations