© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132018
    Prev
    Next
    INDEX
    Explanations

    promise

    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_50_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
    COLOG
    0.38
    緞
    0.36
     нати
    0.35
     Lime
    0.35
    られて
    0.34
    Fox
    0.34
    uyu
    0.34
    ndon
    0.34
    缸
    0.34
    نائي
    0.34
    POSITIVE LOGITS
     promise
    2.45
     Promise
    2.34
     promises
    2.28
    promise
    2.27
    Promise
    2.17
     Promises
    2.13
     promised
    2.11
     обеща
    2.11
    promises
    2.05
    Promises
    1.98
    Activations Density 0.009%

    No Known Activations