© 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. 79880
    Prev
    Next
    INDEX
    Explanations

    usually not serious

    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
    aniu
    0.42
     brigade
    0.39
    ananti
    0.38
    임
    0.38
    icl
    0.37
     unfairly
    0.37
    顼
    0.37
     TN
    0.37
     الانسان
    0.36
     estimados
    0.36
    POSITIVE LOGITS
     స్వ
    0.47
     discret
    0.38
     Exploration
    0.38
     אך
    0.38
     Ey
    0.36
    Termination
    0.36
     termination
    0.36
     مسئلے
    0.35
    ሁ
    0.35
     Arrest
    0.34
    Activations Density 0.015%

    No Known Activations