© 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. 64454
    Prev
    Next
    INDEX
    Explanations

    Just

    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
    Qué
    0.36
    只不过
    0.36
    agements
    0.35
     გადა
    0.34
    朶
    0.33
    Convergence
    0.33
    厉
    0.33
    ↙
    0.33
    یداری
    0.33
     Navigator
    0.32
    POSITIVE LOGITS
     like
    1.04
     như
    0.97
    如
    0.91
     seperti
    0.91
     kuten
    0.90
     जैसे
    0.87
     όπως
    0.87
     كما
    0.86
     как
    0.85
     zoals
    0.84
    Activations Density 0.001%

    No Known Activations