© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159633
    Prev
    Next
    INDEX
    Explanations

    IHL

    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
    is
    1.52
    ми
    1.39
     (
    1.18
    يته
    1.13
    ו
    1.11
    -
    1.09
    اك
    1.06
    1.05
    in
    1.04
    1.04
    POSITIVE LOGITS
     on
    2.09
     up
    1.56
    ב
    1.39
    c
    1.37
     at
    1.31
    त
    1.28
    いた
    1.27
    k
    1.27
    ก
    1.25
    एस
    1.24
    Activations Density 0.000%

    No Known Activations