© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206571
    Prev
    Next
    INDEX
    Explanations

    pepper or tear

    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_46_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
     trident
    0.42
     concreto
    0.41
     ഉട
    0.39
    崠
    0.38
    蹟
    0.38
    odesk
    0.38
     નક્
    0.37
     Friction
    0.37
    偐
    0.37
    runk
    0.36
    POSITIVE LOGITS
     tear
    1.90
     Tear
    1.66
    tear
    1.55
     pepper
    1.20
    Pepper
    1.08
     Pepper
    1.07
    pepper
    1.06
     teard
    1.04
    泪
    1.04
     tears
    1.00
    Activations Density 0.001%

    No Known Activations