© 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. 33079
    Prev
    Next
    INDEX
    Explanations

    instruction followed by task description

    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
     engaging
    0.37
     natives
    0.36
    ഞ
    0.36
    over
    0.36
     fine
    0.36
     shifting
    0.36
     saw
    0.35
    Native
    0.35
    Txt
    0.34
    TXT
    0.34
    POSITIVE LOGITS
    ínt
    0.41
    explanation
    0.38
    ক্ষেত্র
    0.37
     철
    0.36
     Banglades
    0.36
     Krishnam
    0.35
    滋
    0.35
     बेंगल
    0.35
    轰
    0.35
     ინ
    0.34
    Activations Density 0.005%

    No Known Activations