© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241668
    Prev
    Next
    INDEX
    Explanations

    action or process descriptions

    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_25_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
     whose
    0.38
    jší
    0.35
    rass
    0.34
     load
    0.34
    }),
    0.34
    ']),
    0.34
    vq
    0.33
    ř
    0.33
    oload
    0.33
    珩
    0.33
    POSITIVE LOGITS
     niektórych
    0.43
     بعض
    0.40
     niektó
    0.39
     ישראל
    0.38
     ზ
    0.38
     některé
    0.37
     Datensch
    0.37
    𒀉
    0.36
     áreas
    0.36
    andfeel
    0.36
    Activations Density 0.006%

    No Known Activations