© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146247
    Prev
    Next
    INDEX
    Explanations

    instruction phrases / scenarios

    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_0_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
     as
    1.77
    리
    1.33
     are
    1.20
    ру
    1.20
    ные
    1.13
    ３
    1.12
    пу
    1.08
    ale
    1.07
     was
    1.05
    ۳
    1.05
    POSITIVE LOGITS
    ت
    1.77
    t
    1.51
    ,
    1.32
    It
    1.30
    tas
    1.24
    تها
    1.17
    y
    1.17
     It
    1.09
    تون
    1.07
    d
    1.05
    Activations Density 0.000%

    No Known Activations