© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200786
    Prev
    Next
    INDEX
    Explanations

    of a/the/human

    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_37_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
     försö
    0.46
     tentando
    0.43
     طويلة
    0.42
     trying
    0.41
    Trying
    0.41
    善
    0.41
     excelencia
    0.40
    reiben
    0.40
     DIFFIC
    0.39
     attempting
    0.39
    POSITIVE LOGITS
     आरोप
    0.38
     Faun
    0.37
     си
    0.36
     распа
    0.36
     contempt
    0.36
    xiang
    0.36
     этих
    0.35
     তাছাড়া
    0.35
     >=
    0.35
    beb
    0.35
    Activations Density 0.005%

    No Known Activations