© 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. 156772
    Prev
    Next
    INDEX
    Explanations

    speck of dust

    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
     tumbuhan
    0.93
     have
    0.89
    ted
    0.86
    tive
    0.86
    dan
    0.85
    ला
    0.85
    s
    0.82
    لها
    0.82
    ुन
    0.80
    LLA
    0.80
    POSITIVE LOGITS
    ي
    1.12
    "
    1.07
    )،
    0.96
    י
    0.96
    '
    0.95
    is
    0.93
    R
    0.93
    خ
    0.93
    D
    0.92
    ла
    0.91
    Activations Density 0.001%

    No Known Activations