© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253170
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Fletcher
    0.38
     Гра
    0.36
     писа
    0.35
    ቻ
    0.35
    ок
    0.35
    know
    0.34
    kom
    0.33
     کتاب
    0.33
     “
    0.33
     me
    0.33
    POSITIVE LOGITS
     trés
    0.44
    feira
    0.37
    ]["
    0.37
     didnt
    0.37
    ರ್ಚ
    0.37
     śnie
    0.37
     fût
    0.37
    र्च
    0.36
     joh
    0.36
    ibor
    0.36
    Activations Density 0.000%

    No Known Activations