© 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. 205948
    Prev
    Next
    INDEX
    Explanations

    sr =

    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
     telah
    0.43
    Ago
    0.41
    Addo
    0.41
    杼
    0.40
     ankaŭ
    0.39
    prima
    0.39
    簱
    0.39
    toDate
    0.39
     klub
    0.38
    ड़ों
    0.38
    POSITIVE LOGITS
     fossil
    0.41
     initial
    0.40
    if
    0.40
     problematic
    0.39
     Requirement
    0.39
    ل
    0.38
     surprising
    0.38
     بچ
    0.36
     observed
    0.35
     np
    0.35
    Activations Density 0.001%

    No Known Activations