© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124420
    Prev
    Next
    INDEX
    Explanations

    Rosenfeld, Canyon, Glen, feld

    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
    年代
    0.59
    macht
    0.55
    Camp
    0.54
    Namara
    0.54
    1
    0.54
    哨
    0.53
    <0x0D>
    0.52
    部分
    0.52
    Sensor
    0.52
    peek
    0.52
    POSITIVE LOGITS
    өх
    0.70
    이지만
    0.70
     snakes
    0.69
    ۔
    0.69
     tornadoes
    0.67
    غ
    0.66
    н
    0.66
     atteindre
    0.65
    WW
    0.64
    ТО
    0.63
    Activations Density 0.000%

    No Known Activations