© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90960
    Prev
    Next
    INDEX
    Explanations

    grossly offensive or inappropriate

    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_11_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
     বয়ে
    0.51
     moisturizing
    0.50
    με
    0.49
     הד
    0.48
     quedando
    0.48
    come
    0.48
     ד
    0.48
    "/></
    0.48
    mentare
    0.47
    ре
    0.47
    POSITIVE LOGITS
     ES
    0.63
    ES
    0.59
    ёл
    0.58
     ESPE
    0.58
    ని
    0.56
    kis
    0.56
     espe
    0.55
     mám
    0.54
     .”
    0.54
     лока
    0.54
    Activations Density 0.000%

    No Known Activations