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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130554
    Prev
    Next
    INDEX
    Explanations

    table following number

    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
     있는데
    0.39
     있으며
    0.37
     contaminant
    0.37
     탄
    0.35
     globules
    0.35
    trading
    0.35
    بك
    0.34
     acyl
    0.34
     decontamination
    0.34
    enough
    0.34
    POSITIVE LOGITS
     Data
    0.41
    ၢ
    0.39
     seguenti
    0.37
     بنائے
    0.37
     Robbins
    0.37
    halb
    0.36
     nuova
    0.36
     rápida
    0.35
     робити
    0.35
     wichtige
    0.35
    Activations Density 0.000%

    No Known Activations