© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38772
    Prev
    Next
    INDEX
    Explanations

    absence or lack

    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_57_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
     usual
    0.41
    otel
    0.41
    otr
    0.40
     rect
    0.39
    レクトリ
    0.38
     entrants
    0.38
    棚
    0.38
    Alc
    0.37
     sugary
    0.37
     polic
    0.36
    POSITIVE LOGITS
     无
    0.62
    无
    0.55
    without
    0.54
    គ្មាន
    0.51
     不需要
    0.50
     無
    0.50
    無需
    0.50
     без
    0.48
     بغیر
    0.48
     nameless
    0.48
    Activations Density 0.000%

    No Known Activations