© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175896
    Prev
    Next
    INDEX
    Explanations

    behavior

    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_50_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
     KIND
    0.38
     OX
    0.37
     markdown
    0.37
    璽
    0.37
    ifiez
    0.36
    '<
    0.36
     vucc
    0.35
    햇
    0.35
    oxia
    0.35
    oszt
    0.34
    POSITIVE LOGITS
    Behavior
    2.34
     Behavior
    2.31
    行为
    2.31
     Behaviour
    2.30
     behavior
    2.28
     behaviour
    2.25
     behavioral
    2.23
     behavioural
    2.22
     comport
    2.20
     comportement
    2.19
    Activations Density 0.001%

    No Known Activations