© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4929
    Prev
    Next
    INDEX
    Explanations

    PDF metadata and encryption

    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_39_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
    dx
    0.36
     रिक्
    0.33
     embar
    0.32
    embar
    0.32
     su
    0.32
     Peninsula
    0.32
    ̵
    0.32
     financier
    0.31
     confid
    0.31
     किस्
    0.31
    POSITIVE LOGITS
    囘
    0.39
     পাকিস্তানীদের
    0.37
     Prey
    0.36
     semblables
    0.35
    arrer
    0.35
     Hogg
    0.35
     Hester
    0.34
     priming
    0.34
     벡터
    0.34
    🧠
    0.33
    Activations Density 0.001%

    No Known Activations