© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242391
    Prev
    Next
    INDEX
    Explanations

    price ratios / metrics

    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_40_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
    alphabet
    0.41
     quote
    0.39
     margin
    0.38
    흐
    0.38
    _$
    0.37
     weave
    0.36
     свиде
    0.36
     alphabet
    0.36
    руд
    0.35
     सिनेमा
    0.35
    POSITIVE LOGITS
     Wat
    0.52
    ają
    0.43
    awat
    0.42
    waj
    0.42
    insertion
    0.39
     anu
    0.38
     কাশি
    0.38
    íd
    0.38
     Insertion
    0.38
     삽
    0.38
    Activations Density 0.002%

    No Known Activations