© 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. 214975
    Prev
    Next
    INDEX
    Explanations

    oneMethod used: 1

    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
     Leather
    0.41
    렉
    0.40
    を備
    0.37
     रामपुर
    0.36
    lekt
    0.36
    皮革
    0.35
     attraction
    0.35
    បញ្ចប់
    0.35
     phases
    0.35
     rgba
    0.35
    POSITIVE LOGITS
    ហ៊ុន
    0.41
     Macron
    0.41
     onders
    0.40
    鿉
    0.40
     Picard
    0.39
    ĩnh
    0.38
    ையு
    0.38
    ১০
    0.38
    ncoder
    0.38
    條
    0.38
    Activations Density 0.001%

    No Known Activations