© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 432
    Prev
    Next
    INDEX
    Explanations

    RecMethod used: 1Reason: MAX_ACTIVATING_TOKENS are all variations of "Rec"

    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_44_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dela
    0.43
    ೋಷ
    0.42
     RESON
    0.41
    ActivityResult
    0.40
     மந்திர
    0.40
     coag
    0.40
     inlets
    0.39
     Selecting
    0.39
    窰
    0.38
     Strategies
    0.38
    POSITIVE LOGITS
     کم
    0.38
    riot
    0.36
    bier
    0.36
    低
    0.36
    moustache
    0.35
    کم
    0.35
     இதில்
    0.35
    fordern
    0.34
    camouflage
    0.34
    rok
    0.34
    Activations Density 0.027%

    No Known Activations