© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233049
    Prev
    Next
    INDEX
    Explanations

    code snippets and variable names

    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
     }^{(
    0.35
    inx
    0.34
     multimedia
    0.33
    loadFile
    0.33
     anhydride
    0.32
    madan
    0.32
    synth
    0.32
    Synthetic
    0.32
    fileExists
    0.32
     chuyển
    0.32
    POSITIVE LOGITS
     Euler
    0.38
    瘍
    0.37
     Ortiz
    0.36
     Our
    0.34
    ุง
    0.33
     Glück
    0.32
     kone
    0.32
     Grenz
    0.32
     Il
    0.32
     pm
    0.32
    Activations Density 0.001%

    No Known Activations