© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38120
    Prev
    Next
    INDEX
    Explanations

    hundred

    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_57_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
     thousand
    0.84
    thousand
    0.75
    千
    0.70
     Thousand
    0.68
     тыся
    0.63
     हजार
    0.61
    thousands
    0.61
     هزار
    0.59
     тысяч
    0.58
     mille
    0.57
    POSITIVE LOGITS
    백
    0.62
     백
    0.61
     Hon
    0.51
    Hun
    0.51
     hon
    0.50
    hun
    0.47
    HUN
    0.47
     Hund
    0.46
     መ
    0.46
    Hundreds
    0.46
    Activations Density 0.009%

    No Known Activations