© 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. 143238
    Prev
    Next
    INDEX
    Explanations

    vectors

    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
    1.39
    ’
    1.33
    at
    1.31
    that
    1.31
    ب
    1.29
    تها
    1.28
    𝙖
    1.28
    r
    1.25
    s
    1.24
    se
    1.22
    POSITIVE LOGITS
     persoane
    1.34
     Accesat
    1.32
     oude
    1.30
    ور
    1.29
    )\
    1.27
     allemand
    1.27
     ouder
    1.27
     effets
    1.26
     descendants
    1.25
     autres
    1.23
    Activations Density 0.002%

    No Known Activations