© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32317
    Prev
    Next
    INDEX
    Explanations

    list items with context

    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_31_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
    ರುತ್ತದೆ
    0.35
     Impro
    0.34
     improvis
    0.34
     стрелец
    0.33
    MASK
    0.32
    웁
    0.32
     کھی
    0.31
     dismant
    0.31
    ється
    0.31
     নভেম্বর
    0.31
    POSITIVE LOGITS
    antar
    0.38
     перечис
    0.35
     four
    0.33
     princes
    0.33
    四
    0.33
     those
    0.33
    ătate
    0.33
    tron
    0.33
    lima
    0.33
     print
    0.33
    Activations Density 0.017%

    No Known Activations