© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3750
    Prev
    Next
    INDEX
    Explanations

    gl, error, euro, image, verbatim

    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_39_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
    anatom
    0.39
    फ़
    0.38
     أع
    0.38
     Yesus
    0.38
    လိုအပ်
    0.38
    TextChanged
    0.38
    我覺得
    0.38
    ៧
    0.38
    Debugging
    0.37
    োঁয়া
    0.37
    POSITIVE LOGITS
     heels
    0.42
    zingen
    0.36
     Rico
    0.34
     Phong
    0.34
     складу
    0.34
    omass
    0.34
    rtimes
    0.34
     Mercer
    0.34
     Brig
    0.33
    chini
    0.33
    Activations Density 0.000%

    No Known Activations