© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66749
    Prev
    Next
    INDEX
    Explanations

    7

    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
    Least
    0.37
    least
    0.36
     titration
    0.36
     diaria
    0.35
    ariate
    0.34
    cred
    0.34
    ేక
    0.34
     D
    0.33
     Ugly
    0.33
    Cre
    0.33
    POSITIVE LOGITS
    мін
    0.45
     Hartmann
    0.43
     ele
    0.43
     ವೈ
    0.40
     sentiments
    0.40
     Moss
    0.40
     იმ
    0.40
     kib
    0.38
     zeggen
    0.38
     chanc
    0.38
    Activations Density 0.004%

    No Known Activations