© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61802
    Prev
    Next
    INDEX
    Explanations

    narrative

    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_11_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
    2
    0.81
    4
    0.68
    1
    0.65
    6
    0.64
    f
    0.63
    de
    0.61
    we
    0.61
    Sample
    0.60
    Dynamic
    0.60
    F
    0.60
    POSITIVE LOGITS
    থেকে
    0.73
    ਾਸ
    0.73
    तून
    0.62
     सबै
    0.61
    ்ய
    0.59
     ás
    0.58
    杍
    0.58
    ाई
    0.58
     émotion
    0.58
    𝕖
    0.57
    Activations Density 0.002%

    No Known Activations