© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20799
    Prev
    Next
    INDEX
    Explanations

    to

    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_56_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
    教
    0.88
     Say
    0.79
    Say
    0.79
    say
    0.66
     SAY
    0.61
     say
    0.61
     realize
    0.59
     teach
    0.58
     教
    0.58
    说
    0.56
    POSITIVE LOGITS
     sake
    0.36
     causado
    0.35
    㽛
    0.35
     Bouchard
    0.34
    hadow
    0.34
     glass
    0.34
     Glass
    0.33
     유리
    0.33
    OfString
    0.33
     kors
    0.33
    Activations Density 0.001%

    No Known Activations