© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211480
    Prev
    Next
    INDEX
    Explanations

    makes for a type of

    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_19_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
    ().
    0.48
    ل
    0.45
    iden
    0.44
    uke
    0.44
    acterial
    0.44
    ase
    0.43
    ity
    0.43
    offs
    0.43
    le
    0.43
    >(
    0.42
    POSITIVE LOGITS
     편성
    0.52
     Eğitim
    0.52
     Navi
    0.51
     Pode
    0.50
     Qualcomm
    0.50
     Poul
    0.49
     Unt
    0.49
    鏻
    0.49
     Infine
    0.49
     eğitim
    0.48
    Activations Density 0.000%

    No Known Activations