© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62259
    Prev
    Next
    INDEX
    Explanations

    Red Teaming

    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_59_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
    would
    0.40
    ầ
    0.38
    Entities
    0.37
    olids
    0.36
     Wnd
    0.35
    ndo
    0.35
    Would
    0.35
     Lean
    0.35
    MPC
    0.35
    bases
    0.34
    POSITIVE LOGITS
     Whereas
    0.42
     whereas
    0.38
    ٹی
    0.37
     Uganda
    0.36
     continú
    0.36
    Whereas
    0.36
    滾
    0.36
    ټر
    0.35
    ્રોલ
    0.35
    whereas
    0.35
    Activations Density 0.003%

    No Known Activations