© 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. 79502
    Prev
    Next
    INDEX
    Explanations

    evaluations of quality or state

    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
    1.48
    的
    1.48
     are
    1.35
    ви
    1.34
    </h2>
    1.29
    :
    1.22
    ;
    1.20
     à
    1.16
    </h1>
    1.15
    ست
    1.14
    POSITIVE LOGITS
    する
    1.40
    ี
    1.34
    示す
    1.33
    ר
    1.29
    larni
    1.24
    u
    1.22
    تری
    1.19
    tól
    1.17
    ิ
    1.16
    speople
    1.14
    Activations Density 0.000%

    No Known Activations