© 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. 142330
    Prev
    Next
    INDEX
    Explanations

    repeated "zu"

    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
     I
    1.94
    '
    1.63
     R
    1.43
    н
    1.38
     T
    1.38
     N
    1.32
    )،
    1.32
     L
    1.29
     B
    1.27
     O
    1.27
    POSITIVE LOGITS
    ing
    1.97
    g
    1.77
    ,
    1.52
    the
    1.50
    h
    1.45
    d
    1.41
     is
    1.40
    tedir
    1.37
    den
    1.34
    ties
    1.25
    Activations Density 0.000%

    No Known Activations