© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90121
    Prev
    Next
    INDEX
    Explanations

    Oh my gosh / Oh my God

    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
    z
    0.88
    l
    0.79
    m
    0.78
    3
    0.72
    k
    0.69
    Buyers
    0.68
    t
    0.66
    )*
    0.65
    -
    0.65
    dash
    0.64
    POSITIVE LOGITS
    indeki
    0.70
     biochemical
    0.67
     provocation
    0.62
     superficial
    0.61
     veiled
    0.61
     transformations
    0.61
     perverse
    0.59
     façade
    0.58
     physicochemical
    0.58
     epidermis
    0.58
    Activations Density 0.001%

    No Known Activations