© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91368
    Prev
    Next
    INDEX
    Explanations

    Panasonic

    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_11_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
    க்
    0.51
    le
    0.50
     présent
    0.43
    Function
    0.41
    since
    0.40
     Arac
    0.40
    ي
    0.40
    talking
    0.39
    Қ
    0.38
    ى
    0.38
    POSITIVE LOGITS
     vowed
    0.54
     vows
    0.49
     ashore
    0.47
     Giulia
    0.47
     segni
    0.46
     wurden
    0.46
    scrollY
    0.44
     Sardinia
    0.44
     purged
    0.44
     aggrav
    0.43
    Activations Density 0.038%

    No Known Activations