© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39683
    Prev
    Next
    INDEX
    Explanations

    Unit or Type

    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_57_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
    FIVE
    0.71
     four
    0.71
    五
    0.70
     FIVE
    0.69
    六
    0.67
    six
    0.66
     six
    0.66
    SIX
    0.66
     quatro
    0.65
     FOUR
    0.65
    POSITIVE LOGITS
     ris
    0.40
     maya
    0.39
    brett
    0.38
     cần
    0.38
     myself
    0.37
     antih
    0.37
     finde
    0.37
     grupa
    0.37
    мат
    0.37
    ⦁
    0.36
    Activations Density 0.000%

    No Known Activations