© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 88564
    Prev
    Next
    INDEX
    Explanations

    rising prices

    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_3_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
    り
    0.64
    ട
    0.64
    রা
    0.63
    ด
    0.62
     Europese
    0.61
     speriment
    0.60
     lista
    0.59
     squadron
    0.58
    ב
    0.57
    ง่าย
    0.57
    POSITIVE LOGITS
    a
    0.80
     effecting
    0.66
    rations
    0.63
    Y
    0.60
    Au
    0.58
    études
    0.58
    bears
    0.57
    Dreams
    0.57
    Dong
    0.56
    extent
    0.54
    Activations Density 0.000%

    No Known Activations