© 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. 36400
    Prev
    Next
    INDEX
    Explanations

    galaxy clusters and watches

    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
    ك
    0.84
    at
    0.82
    어
    0.77
    ت
    0.76
    ం
    0.74
    ين
    0.71
    ת
    0.71
    ané
    0.68
    حق
    0.66
    y
    0.66
    POSITIVE LOGITS
    Percent
    0.75
    Jenis
    0.70
    ifference
    0.68
     Variablen
    0.66
    difference
    0.66
    localPosition
    0.65
     Rồi
    0.64
     Breeders
    0.64
    percent
    0.64
    degener
    0.63
    Activations Density 0.001%

    No Known Activations