© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209122
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases

    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_10_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
    ために
    0.63
    ափ
    0.56
    от
    0.55
    حدیث
    0.54
    모델
    0.52
    При
    0.52
    у
    0.52
    при
    0.50
    models
    0.50
    پی
    0.50
    POSITIVE LOGITS
     MRI
    0.46
    b
    0.44
     лиш
    0.44
    סף
    0.44
     intuitive
    0.44
     é
    0.43
     množství
    0.43
     positives
    0.43
     transparent
    0.43
     Though
    0.42
    Activations Density 0.000%

    No Known Activations