© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9273
    Prev
    Next
    INDEX
    Explanations

    statistical analysis software

    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_13_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
     o
    0.55
    idad
    0.50
    udence
    0.49
    ramework
    0.48
    \
    0.48
    iousness
    0.46
    нього
    0.45
    aculture
    0.44
    њу
    0.42
    frame
    0.42
    POSITIVE LOGITS
    出现
    0.59
     xong
    0.59
     asistente
    0.59
    거
    0.57
     Quelles
    0.57
     kttt
    0.57
    髌
    0.57
     vagin
    0.56
     wher
    0.56
     vào
    0.56
    Activations Density 0.087%

    No Known Activations