© 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. 40201
    Prev
    Next
    INDEX
    Explanations

    mess up or mess with

    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
     contagious
    0.69
     gebo
    0.65
     haremos
    0.62
    𝘃
    0.61
     malicious
    0.60
     customary
    0.59
     freien
    0.58
    кает
    0.58
    ным
    0.58
    ಿತ
    0.58
    POSITIVE LOGITS
    ون
    0.88
    .
    0.70
    -
    0.68
    ama
    0.63
    n
    0.60
    Whatever
    0.59
    Although
    0.58
    |+
    0.58
    ன்
    0.57
    >
    0.57
    Activations Density 0.002%

    No Known Activations