© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14688
    Prev
    Next
    INDEX
    Explanations

    general knowledge

    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
     consume
    0.40
     راست
    0.40
    كري
    0.39
     पार्श्व
    0.38
    素
    0.37
     Zhen
    0.37
    луч
    0.37
    ்ச
    0.36
    पत्
    0.36
     تس
    0.36
    POSITIVE LOGITS
    탬
    0.41
     Ото
    0.38
    َى
    0.37
     McGill
    0.37
    knowledge
    0.36
    知識
    0.36
     keb
    0.36
     individuals
    0.35
     Cardinal
    0.35
     Edinburgh
    0.35
    Activations Density 0.001%

    No Known Activations