© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33745
    Prev
    Next
    INDEX
    Explanations

    frontier justice and setting

    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_7_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
     لے
    0.22
     “,
    0.22
     šta
    0.21
    áról
    0.20
    и
    0.20
     هڪ
    0.20
    ين
    0.20
     چې
    0.20
    ական
    0.19
     ۽
    0.19
    POSITIVE LOGITS
     the
    0.35
    ق
    0.32
    ك
    0.31
     this
    0.30
    the
    0.30
    as
    0.29
    -
    0.29
    </h3>
    0.27
    ки
    0.26
    efeller
    0.26
    Activations Density 0.000%

    No Known Activations