© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76954
    Prev
    Next
    INDEX
    Explanations

    email subject lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    idence
    0.38
     cerebro
    0.38
     authToken
    0.38
     moder
    0.37
     ipotesi
    0.37
    증
    0.37
     Moder
    0.37
     hypothesis
    0.37
    ដ្ឋ
    0.37
     Moderator
    0.37
    POSITIVE LOGITS
    狗
    0.38
     неот
    0.37
    क्षित
    0.37
     unfl
    0.37
     grey
    0.36
    ロゴ
    0.35
    égi
    0.35
     assin
    0.35
     संपर्क
    0.34
    éricas
    0.34
    Activations Density 0.001%

    No Known Activations