© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158151
    Prev
    Next
    INDEX
    Explanations

    add-ons

    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_2_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
    ي
    1.18
    ل
    0.95
    ↵
    0.92
     gră
    0.92
    ਾ
    0.91
     сдела
    0.91
     divergents
    0.90
     dirigeants
    0.89
     décrire
    0.89
     carinatis
    0.88
    POSITIVE LOGITS
    1
    1.30
    0
    1.02
    .
    0.98
    ado
    0.97
    I
    0.93
    G
    0.91
    U
    0.89
    the
    0.86
    taining
    0.84
     of
    0.84
    Activations Density 0.000%

    No Known Activations