© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124625
    Prev
    Next
    INDEX
    Explanations

    blue screen or hole

    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
    ،
    0.77
    ބ
    0.64
    ޒ
    0.64
    -
    0.63
    ，
    0.61
    ８
    0.61
    掄
    0.60
     marít
    0.60
    );
    0.59
    වින්
    0.59
    POSITIVE LOGITS
    s
    1.14
    t
    1.00
    r
    0.93
    the
    0.86
    l
    0.80
    కు
    0.78
    ів
    0.75
    т
    0.74
     in
    0.70
    ों
    0.70
    Activations Density 0.001%

    No Known Activations