© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123033
    Prev
    Next
    INDEX
    Explanations

    personality test

    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_3_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
    ل
    0.72
    い
    0.62
     alters
    0.55
    لها
    0.53
    ة
    0.53
     Empowerment
    0.52
    禳
    0.51
     sogar
    0.51
    igns
    0.50
    ，“
    0.50
    POSITIVE LOGITS
    0
    0.69
    with
    0.63
     холо
    0.60
    an
    0.57
    classical
    0.57
    t
    0.57
    9
    0.56
     наук
    0.55
     courtes
    0.55
    catalog
    0.55
    Activations Density 0.001%

    No Known Activations