© 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. 84065
    Prev
    Next
    INDEX
    Explanations

    Q followed by diverse characters

    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
    <0x80>
    1.15
    áme
    1.09
     (
    1.05
    дная
    1.05
    ě
    1.01
     Kommune
    0.99
     finalizar
    0.98
     It
    0.98
    دت
    0.98
    okkal
    0.98
    POSITIVE LOGITS
    on
    1.86
    3
    1.80
    2
    1.72
    다
    1.63
    ا
    1.63
    る
    1.59
    ३
    1.55
    е
    1.52
    ע
    1.48
    о
    1.47
    Activations Density 0.001%

    No Known Activations