© 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. 27066
    Prev
    Next
    INDEX
    Explanations

    size =

    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
    MA
    0.43
     Hald
    0.41
     getters
    0.37
    imated
    0.36
    叩
    0.36
    DECL
    0.36
    ME
    0.35
     হাজ
    0.35
    popup
    0.35
    FOUND
    0.34
    POSITIVE LOGITS
     multicultural
    0.40
    的精神
    0.40
     paar
    0.38
     solicitor
    0.38
     Solicitors
    0.38
     Сак
    0.38
     accomp
    0.38
     Mug
    0.38
    Cue
    0.38
    桑
    0.37
    Activations Density 0.001%

    No Known Activations