© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208033
    Prev
    Next
    INDEX
    Explanations

    regex for email addresses

    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_25_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
     metų
    0.41
     doel
    0.38
     jedes
    0.38
     עד
    0.37
    厙
    0.37
    ᴬ
    0.37
    㢄
    0.37
     boje
    0.36
     latéral
    0.36
    녁
    0.36
    POSITIVE LOGITS
    IBM
    0.39
    grant
    0.38
    Children
    0.37
    reas
    0.36
    cur
    0.35
    back
    0.35
     */
    0.35
    Grant
    0.34
    healing
    0.34
    当
    0.34
    Activations Density 0.002%

    No Known Activations