© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253099
    Prev
    Next
    INDEX
    Explanations

    a

    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
     chances
    0.42
     understands
    0.40
     understand
    0.40
    Understand
    0.39
     chance
    0.37
     Understand
    0.37
    ́n
    0.36
    ்
    0.35
     Chances
    0.34
     шан
    0.33
    POSITIVE LOGITS
     feeling
    2.41
    feeling
    2.25
     Feeling
    2.14
    Feeling
    2.13
     Gefühl
    1.66
     gevoel
    1.46
     чувство
    1.36
    感觉
    1.30
     FEEL
    1.24
     sensação
    1.23
    Activations Density 0.000%

    No Known Activations