© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15868
    Prev
    Next
    INDEX
    Explanations

    "And God" or "form action"

    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_34_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
    mut
    0.44
    aktan
    0.38
     malam
    0.38
    겉
    0.34
    owntown
    0.34
     glaze
    0.34
    aldi
    0.34
     গায়ে
    0.34
    夕
    0.34
     silver
    0.34
    POSITIVE LOGITS
     Diffraction
    0.44
     ಮಟ್ಟ
    0.39
     Syst
    0.39
     Beale
    0.38
     ስርዓ
    0.38
    㐸
    0.37
    粱
    0.36
     Funcion
    0.35
    rnn
    0.35
     Shroff
    0.35
    Activations Density 0.014%

    No Known Activations