© 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. 236800
    Prev
    Next
    INDEX
    Explanations

    Gemma team at Google DeepMind

    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
     realidade
    0.46
     réalité
    0.41
     собственных
    0.40
    ֜
    0.40
     realidad
    0.38
     naprawdę
    0.38
     ແລະ
    0.37
     realtà
    0.37
     പിന്നെ
    0.36
    porque
    0.36
    POSITIVE LOGITS
     K
    0.39
     부담
    0.39
     Audio
    0.39
     peaks
    0.38
     variants
    0.38
     Modified
    0.38
     Peak
    0.37
     variant
    0.37
     Mirror
    0.37
    აში
    0.37
    Activations Density 0.004%

    No Known Activations