© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235224
    Prev
    Next
    INDEX
    Explanations

    creating vapor

    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_32_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
    橢
    0.39
     Gla
    0.37
     புது
    0.36
     Macs
    0.36
    EO
    0.35
     microphones
    0.35
    macd
    0.35
    喍
    0.35
     Mic
    0.34
     photographers
    0.34
    POSITIVE LOGITS
     attaching
    0.38
     vapor
    0.36
    锒
    0.36
    ...\
    0.36
     Operate
    0.34
     వ
    0.34
     සම
    0.34
    バージ
    0.34
     vapour
    0.33
     vapors
    0.33
    Activations Density 0.005%

    No Known Activations