© 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. 44309
    Prev
    Next
    INDEX
    Explanations

    tide, clock, forces, Wiki, flats

    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
    0
    1.05
    д
    0.79
     entier
    0.67
    EY
    0.67
    أ
    0.65
     amplification
    0.64
    ك
    0.64
     have
    0.61
     hebben
    0.59
     abril
    0.59
    POSITIVE LOGITS
    ر
    0.74
    ain
    0.63
     Tide
    0.62
    ва
    0.61
    rates
    0.61
    ymethyl
    0.58
    רים
    0.58
    starts
    0.56
    راب
    0.55
    رسٹ
    0.55
    Activations Density 0.011%

    No Known Activations