© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 81395
    Prev
    Next
    INDEX
    Explanations

    key in code definition or 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_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
    ת
    1.45
    т
    1.41
    ш
    1.38
    лі
    1.38
    л
    1.37
     of
    1.33
    י
    1.25
    ي
    1.22
    ש
    1.21
    2
    1.20
    POSITIVE LOGITS
    f
    1.39
    the
    1.37
    r
    1.27
    
    1.13
    𝟎
    1.12
    in
    1.11
    m
    1.09
    ۰
    1.09
    0
    1.08
    g
    1.07
    Activations Density 0.003%

    No Known Activations