© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102031
    Prev
    Next
    INDEX
    Explanations

    researcher

    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_14_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
     Jing
    0.53
     Kentucky
    0.51
    ができる
    0.51
     వర
    0.50
     से
    0.49
    𝒜
    0.48
     Connecticut
    0.48
     Buildable
    0.47
     McGr
    0.47
    𝒟
    0.46
    POSITIVE LOGITS
    PLEASE
    0.48
     miejsce
    0.48
    ');
    0.47
    オート
    0.46
    c
    0.46
    Pho
    0.46
    self
    0.45
    ')
    0.45
    lang
    0.44
    ל
    0.44
    Activations Density 0.001%

    No Known Activations