© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22327
    Prev
    Next
    INDEX
    Explanations

    code operations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    um
    0.50
    umed
    0.49
    viz
    0.46
     viz
    0.46
    Viz
    0.44
     Viz
    0.43
    iroz
    0.41
    ⁉
    0.40
    odies
    0.39
     уме
    0.38
    POSITIVE LOGITS
    itted
    0.44
     खाते
    0.43
    笈
    0.39
    ithi
    0.39
    әп
    0.38
     पश्चात
    0.36
     côté
    0.35
    持久
    0.35
    ベーション
    0.35
    icode
    0.34
    Activations Density 0.016%

    No Known Activations