© 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. 166863
    Prev
    Next
    INDEX
    Explanations

    but

    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
     misuse
    0.64
     recklessly
    0.59
     careless
    0.59
     carelessness
    0.57
     abuse
    0.57
    濫
    0.54
     लापरवाही
    0.53
     abuso
    0.52
     abused
    0.51
     carelessly
    0.51
    POSITIVE LOGITS
    皎
    0.37
     சாத
    0.36
    装置
    0.36
    PERTIES
    0.36
     Reach
    0.36
    utches
    0.35
     granules
    0.35
     हाइड्रोजन
    0.34
     Gran
    0.34
     énerg
    0.34
    Activations Density 0.038%

    No Known Activations