© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213743
    Prev
    Next
    INDEX
    Explanations

    Irritation

    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_47_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
    SystemFileSystem
    0.41
    ashed
    0.39
    ﺙ
    0.38
    жено
    0.37
    న్నా
    0.36
     hv
    0.35
    ᅴ
    0.35
     εφ
    0.35
    łac
    0.35
    dala
    0.35
    POSITIVE LOGITS
     irr
    0.47
     Ir
    0.45
    Irr
    0.43
     irrit
    0.42
     IRR
    0.41
     ir
    0.40
    Ir
    0.40
     Irrigation
    0.39
     iridium
    0.39
     Irene
    0.38
    Activations Density 0.001%

    No Known Activations