© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244123
    Prev
    Next
    INDEX
    Explanations

    python discord bot

    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_40_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
     apt
    0.38
    .??.??"]
    0.37
    planet
    0.37
     Schaden
    0.36
     filede
    0.36
    programmed
    0.35
    Տ
    0.35
    ledo
    0.35
    тою
    0.35
    palindrome
    0.35
    POSITIVE LOGITS
    тельств
    0.40
     caroten
    0.40
     roasting
    0.39
     oysters
    0.39
     显示
    0.38
    améli
    0.37
    aré
    0.37
    幣
    0.37
     roast
    0.36
     outdoors
    0.36
    Activations Density 0.000%

    No Known Activations