© 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. 42363
    Prev
    Next
    INDEX
    Explanations

    ango

    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
    '
    0.79
    ו
    0.77
    ються
    0.74
    وة
    0.66
     orbiting
    0.66
     остров
    0.64
    ین
    0.63
     castration
    0.63
    šao
    0.63
    تين
    0.62
    POSITIVE LOGITS
    de
    0.99
    th
    0.94
    ere
    0.94
    3
    0.91
    ri
    0.89
    ta
    0.88
    re
    0.85
    /
    0.85
    ty
    0.84
    kan
    0.80
    Activations Density 0.000%

    No Known Activations