© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218658
    Prev
    Next
    INDEX
    Explanations

    say sorry

    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_47_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
     choking
    0.38
    чны
    0.36
     esim
    0.36
    ̃
    0.36
     Satan
    0.36
    ularis
    0.35
    €¦
    0.35
    Curtis
    0.35
    income
    0.35
    eka
    0.34
    POSITIVE LOGITS
     authentically
    0.38
     വളരെ
    0.37
    UTH
    0.37
    貿
    0.37
     culinary
    0.37
     unsuitable
    0.37
     properly
    0.36
     довольно
    0.36
    𝔀
    0.36
    躡
    0.36
    Activations Density 0.003%

    No Known Activations