© 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. 24185
    Prev
    Next
    INDEX
    Explanations

    Youth

    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
     sphincter
    0.45
     freeze
    0.41
    冻
    0.40
     LHS
    0.40
     ሀ
    0.39
     freezes
    0.39
     hjel
    0.39
    狮
    0.38
     |=
    0.38
    rafish
    0.38
    POSITIVE LOGITS
     desenvolved
    0.41
     desarroll
    0.40
     Desenvolvimento
    0.39
    깽
    0.39
    Developer
    0.38
    Developers
    0.38
     desenvolvimento
    0.38
     Desarrollo
    0.38
     desarrollo
    0.38
     Development
    0.37
    Activations Density 0.008%

    No Known Activations