© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154077
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     dará
    0.56
     den
    0.52
     dem
    0.52
     ду
    0.52
    -
    0.51
     dr
    0.50
    -',
    0.49
     x
    0.49
     ö
    0.49
     du
    0.48
    POSITIVE LOGITS
    Ag
    0.81
    AG
    0.73
     Ag
    0.66
    sensitivity
    0.65
    sensitive
    0.63
    agm
    0.62
     Αγ
    0.57
    ag
    0.54
    Sensitivity
    0.53
    empty
    0.53
    Activations Density 0.001%

    No Known Activations