© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142122
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     बह
    0.41
    vature
    0.37
    ாண
    0.37
    Victory
    0.36
    tke
    0.36
    Objective
    0.35
    ґ
    0.35
     operar
    0.34
     Wentworth
    0.34
    eva
    0.34
    POSITIVE LOGITS
     binomial
    0.39
     few
    0.38
     محیط
    0.36
    보험
    0.35
     స్వ
    0.35
     गुन
    0.35
     glu
    0.34
     sets
    0.34
    ଗ
    0.34
     گلو
    0.34
    Activations Density 0.023%

    No Known Activations