© 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. 160402
    Prev
    Next
    INDEX
    Explanations

    mathematical latex formatting

    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
     {
    1.66
     $
    1.40
     +
    1.27
    ি
    1.25
    ד
    1.25
    <0x80>
    1.23
     <
    1.21
     }
    1.20
     powied
    1.20
    ى
    1.18
    POSITIVE LOGITS
    in
    1.37
    inį
    1.10
    kannya
    1.05
    nés
    1.03
    ée
    1.02
    kke
    0.97
    ियां
    0.95
    óság
    0.95
    ado
    0.92
    .
    0.89
    Activations Density 0.037%

    No Known Activations