© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176558
    Prev
    Next
    INDEX
    Explanations

    movies and actors

    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_50_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
     मर्ज
    0.40
    Alessandro
    0.40
    芢
    0.40
     glyc
    0.39
     Fargo
    0.38
     rods
    0.38
     giardino
    0.38
    ttino
    0.38
     Alessandro
    0.37
    俢
    0.37
    POSITIVE LOGITS
    част
    0.39
     damaging
    0.36
     precedent
    0.36
    чил
    0.36
     प्रिया
    0.36
    iola
    0.35
     stressing
    0.35
     Bona
    0.35
    colorPrimary
    0.35
     Blau
    0.34
    Activations Density 0.000%

    No Known Activations