© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227308
    Prev
    Next
    INDEX
    Explanations

    more than

    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_6_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
    ор
    0.87
     infantile
    0.85
    і
    0.85
    ем
    0.84
    اری
    0.82
    ίας
    0.79
     pharmaceut
    0.78
     thuốc
    0.77
     rối
    0.76
     ένα
    0.76
    POSITIVE LOGITS
    to
    1.39
    de
    1.19
    ד
    1.10
    ל
    1.09
    T
    1.05
    K
    1.05
    val
    1.02
    ما
    1.02
    A
    1.00
    R
    1.00
    Activations Density 0.001%

    No Known Activations