© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130228
    Prev
    Next
    INDEX
    Explanations

    Mand, mandatory, mandate, Mandala

    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_1_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
     of
    1.30
     brasile
    1.05
    p
    1.04
    al
    1.02
    of
    1.02
    n
    1.02
    _
    0.97
    я
    0.96
     Decreto
    0.93
     integrante
    0.92
    POSITIVE LOGITS
    I
    1.44
    V
    1.34
    B
    1.31
    И
    1.29
    W
    1.28
    N
    1.25
    C
    1.24
    It
    1.21
    Time
    1.21
    5
    1.21
    Activations Density 0.000%

    No Known Activations