© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11503
    Prev
    Next
    INDEX
    Explanations

    abstract precedes colon

    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_40_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
    ദ്ര
    0.40
    াড়ার
    0.39
     Fathers
    0.37
    乱流
    0.37
    ﯾ
    0.37
     लड़
    0.37
    pregn
    0.37
    jdt
    0.36
    働く
    0.36
    槨
    0.36
    POSITIVE LOGITS
     motivational
    0.58
    Motivation
    0.54
     motivation
    0.53
     motivating
    0.53
    mot
    0.52
    motivation
    0.52
    Motivational
    0.52
    Mot
    0.51
     motivations
    0.51
     Motivation
    0.50
    Activations Density 0.001%

    No Known Activations