© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61232
    Prev
    Next
    INDEX
    Explanations

    treated as

    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
    م
    1.48
    ्या
    1.14
    ج
    1.12
    ного
    1.10
    ق
    1.07
     effectuer
    1.05
    ä
    1.04
    حت
    1.03
    ן
    1.02
     atteint
    1.02
    POSITIVE LOGITS
    IN
    1.39
    H
    1.36
    O
    1.30
    al
    1.28
    ।
    1.28
    la
    1.25
    ма
    1.13
    EL
    1.13
    7
    1.10
    。
    1.09
    Activations Density 0.002%

    No Known Activations