© 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. 208420
    Prev
    Next
    INDEX
    Explanations

    Finally

    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_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
     our
    0.54
     ):
    0.52
     :'
    0.50
     then
    0.49
     :
    0.48
     nuestra
    0.46
     :}
    0.46
     :\
    0.46
    我們的
    0.45
     obras
    0.45
    POSITIVE LOGITS
     ćemo
    0.42
    will
    0.42
    」，
    0.41
     ćete
    0.40
    会在
    0.40
     बताएंगे
    0.39
     করবে
    0.39
     —
    0.39
     करेंगे
    0.39
     će
    0.38
    Activations Density 0.002%

    No Known Activations