© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23146
    Prev
    Next
    INDEX
    Explanations

    opening curly brace

    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
     (\"
    0.89
     (“
    0.75
     („
    0.69
     («
    0.64
    (“
    0.59
    ..”
    0.54
     ('
    0.52
    {\"
    0.52
    ？”
    0.51
    ...”
    0.51
    POSITIVE LOGITS
     "
    0.47
     ".
    0.42
     কারণে
    0.42
     "":
    0.41
     ":
    0.40
     :
    0.40
    餒
    0.39
     evaded
    0.38
     позволит
    0.37
     serpent
    0.36
    Activations Density 0.006%

    No Known Activations