© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42069
    Prev
    Next
    INDEX
    Explanations

    H.R. Giger style, wallpaper, HDInsight, BoxLayout

    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
    u
    0.80
    t
    0.80
    st
    0.75
    los
    0.74
    ുണ്ട
    0.72
    전
    0.68
    tion
    0.68
    with
    0.67
    twenty
    0.65
    leer
    0.64
    POSITIVE LOGITS
     macchina
    0.57
     एचडी
    0.56
     galaxy
    0.53
     godina
    0.52
     konci
    0.51
    ằ
    0.50
     vecino
    0.50
     heroic
    0.50
    udah
    0.49
    いますが
    0.49
    Activations Density 0.006%

    No Known Activations