© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145426
    Prev
    Next
    INDEX
    Explanations

    barefoot walking on surfaces

    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
    c
    1.52
    u
    1.29
    ض
    1.29
    as
    1.27
    ar
    1.24
     опреде
    1.23
     chính
    1.19
     hypothesize
    1.19
    k
    1.19
    F
    1.16
    POSITIVE LOGITS
    of
    1.80
     are
    1.58
     is
    1.53
     was
    1.53
    ни
    1.50
    <0x0D>
    1.48
    0
    1.43
    اً
    1.37
    ০
    1.27
    ENT
    1.20
    Activations Density 0.000%

    No Known Activations