© 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. 35874
    Prev
    Next
    INDEX
    Explanations

    I have had the opportunity to

    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
    banking
    0.39
     खारिज
    0.39
     ardından
    0.38
     banking
    0.38
     günlük
    0.38
    সম্প্রতি
    0.37
    Banking
    0.37
    튿
    0.37
     후에
    0.36
    いつ
    0.36
    POSITIVE LOGITS
     Asturias
    0.40
    MaxPool
    0.39
    ляти
    0.39
     Crock
    0.38
     Bergman
    0.37
     empires
    0.37
     reside
    0.37
     vivere
    0.36
    ilius
    0.36
     crescere
    0.35
    Activations Density 0.001%

    No Known Activations