© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129419
    Prev
    Next
    INDEX
    Explanations

    original content generation

    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_1_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
     be
    1.34
    ش
    1.13
    L
    1.09
    ET
    1.04
     {
    1.02
    ü
    0.99
    S
    0.98
    ັບ
    0.96
     quantité
    0.92
    ви
    0.91
    POSITIVE LOGITS
    ↵↵
    1.27
    .
    1.05
    ak
    1.00
    ির
    1.00
    are
    0.97
    지
    0.96
    мимо
    0.91
    alities
    0.89
    리의
    0.89
    ి
    0.88
    Activations Density 0.005%

    No Known Activations