© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111945
    Prev
    Next
    INDEX
    Explanations

    german verbs

    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_2_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
    '
    2.14
    '،
    1.27
    ’
    1.15
    "،
    1.11
    )،
    1.10
    ،
    1.08
    '।
    1.02
    '";
    0.99
    <0x80>
    0.95
    ，
    0.94
    POSITIVE LOGITS
    ad
    1.19
    ן
    1.16
    é
    1.09
    де
    1.07
    ul
    1.04
    ے
    0.99
    ay
    0.98
    ز
    0.98
    ین
    0.98
    ेशन
    0.95
    Activations Density 0.000%

    No Known Activations