© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125156
    Prev
    Next
    INDEX
    Explanations

    i'm glad

    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
    ன்
    0.73
    म
    0.73
     کمار
    0.67
    am
    0.65
    বাবুর
    0.65
    বাবু
    0.63
    मारा
    0.63
    ING
    0.63
    enna
    0.61
    𝗹
    0.61
    POSITIVE LOGITS
    >
    0.86
    og
    0.65
     cataly
    0.64
     ου
    0.64
    ow
    0.62
     (
    0.60
     to
    0.59
    sst
    0.59
     beho
    0.58
    ิ
    0.58
    Activations Density 0.000%

    No Known Activations