© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158056
    Prev
    Next
    INDEX
    Explanations

    medium-high

    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_2_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
     powied
    1.27
    т
    1.20
    ت
    1.16
    ي
    1.13
    x
    1.10
     написа
    1.08
    י
    1.08
    t
    1.07
    ;$
    1.06
     фара
    1.03
    POSITIVE LOGITS
    in
    1.40
    在
    1.08
    u
    0.98
    도
    0.97
    च्या
    0.95
    :
    0.94
     a
    0.93
    ul
    0.92
    ও
    0.89
    為
    0.88
    Activations Density 0.003%

    No Known Activations