© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81974
    Prev
    Next
    INDEX
    Explanations

    Dutch

    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_53_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
     counterpart
    0.51
     tegen
    0.49
     kontra
    0.46
     t
    0.44
    counter
    0.43
     counterparts
    0.42
     flourish
    0.42
     Fu
    0.39
    dow
    0.39
    journey
    0.39
    POSITIVE LOGITS
     Phases
    0.40
    мых
    0.38
     выра
    0.37
     naked
    0.37
     लाए
    0.37
     음
    0.36
     liable
    0.36
     ല
    0.36
    นั้น
    0.35
    ম্
    0.35
    Activations Density 0.000%

    No Known Activations