© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80104
    Prev
    Next
    INDEX
    Explanations

    navigating challenges

    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_0_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
    ла
    2.05
    ۰
    1.75
    ма
    1.50
    ட்ட
    1.44
    с
    1.44
    лин
    1.41
    يح
    1.34
    л
    1.33
    يون
    1.31
    يج
    1.30
    POSITIVE LOGITS
    \
    1.57
    c
    1.52
    k
    1.45
    the
    1.40
    t
    1.38
    (
    1.27
    n
    1.24
     assis
    1.16
    क
    1.09
     institu
    1.08
    Activations Density 0.001%

    No Known Activations