© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239925
    Prev
    Next
    INDEX
    Explanations

    "keeping" followed by "the"

    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
    ાસ
    0.46
     ନ
    0.45
     récente
    0.43
    変
    0.43
     récent
    0.42
     păr
    0.40
     人気
    0.39
    值
    0.38
    ابہ
    0.38
     sort
    0.37
    POSITIVE LOGITS
    стика
    0.46
     Swimming
    0.41
    Swimming
    0.39
    лены
    0.38
    шей
    0.38
    tul
    0.37
    Demand
    0.36
    timed
    0.36
     Tull
    0.36
     должны
    0.35
    Activations Density 0.000%

    No Known Activations