© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38337
    Prev
    Next
    INDEX
    Explanations

    HellaSwag

    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_3_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
    us
    0.71
    Então
    0.66
    ని
    0.65
    ্
    0.64
    ک
    0.62
    Buenas
    0.61
    Wm
    0.60
    м
    0.60
    ্ক
    0.59
    Then
    0.57
    POSITIVE LOGITS
     can
    0.70
    u
    0.64
     ricevere
    0.62
     biel
    0.60
     penj
    0.59
    大
    0.58
    uden
    0.58
    哔
    0.57
    कर्ष
    0.55
     ব্যয়ে
    0.55
    Activations Density 0.000%

    No Known Activations