© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41305
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units like feet

    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
     diminutive
    0.91
    ificateur
    0.75
    inį
    0.72
     is
    0.70
    imeter
    0.70
    ificador
    0.67
    ίναι
    0.66
    浅
    0.66
    ᅬ
    0.66
     synonymous
    0.64
    POSITIVE LOGITS
    ،
    0.97
     It
    0.90
    It
    0.87
    EO
    0.85
    .,
    0.83
    to
    0.82
    、
    0.81
    ၊
    0.79
    Answer
    0.78
    ק
    0.78
    Activations Density 0.024%

    No Known Activations