© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220082
    Prev
    Next
    INDEX
    Explanations

    html input type

    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_31_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
    颉
    0.41
    عين
    0.35
    ాని
    0.34
     ಅಧಿಕಾರಿ
    0.34
     ಆತ್ಮ
    0.33
    මින්
    0.33
     Importing
    0.33
     spokoj
    0.33
     спокойно
    0.33
     REQUIRED
    0.32
    POSITIVE LOGITS
    ('-',
    0.41
    擦
    0.37
     ան
    0.37
    滁
    0.36
    irlas
    0.35
    forgettable
    0.35
    utzerklärung
    0.34
    icles
    0.33
     â
    0.33
     sujet
    0.33
    Activations Density 0.000%

    No Known Activations