© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53091
    Prev
    Next
    INDEX
    Explanations

    how much

    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_31_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
     stabbed
    0.39
     knife
    0.38
     À
    0.36
    শায়
    0.35
    stw
    0.34
    蛰
    0.34
     استخدم
    0.33
    coup
    0.33
    uncak
    0.33
     tjän
    0.33
    POSITIVE LOGITS
     Too
    0.52
    Too
    0.47
     too
    0.46
    too
    0.42
     demasiado
    0.42
     terlalu
    0.41
     Enough
    0.41
    太
    0.40
     demasi
    0.39
    enough
    0.38
    Activations Density 0.035%

    No Known Activations