© 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. 166425
    Prev
    Next
    INDEX
    Explanations

    I apologize that I cannot

    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
    以后
    0.40
     damning
    0.38
     devastating
    0.38
    fatal
    0.38
    abhavam
    0.38
     malheureusement
    0.38
    酩
    0.38
    ष्मा
    0.38
     Exams
    0.38
     fatally
    0.37
    POSITIVE LOGITS
    देशक
    0.39
     adaptable
    0.38
    į
    0.35
    Does
    0.35
    Regional
    0.35
     jie
    0.35
     Regional
    0.34
    があれば
    0.34
    补
    0.34
    🧣
    0.33
    Activations Density 0.001%

    No Known Activations