© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1598
    Prev
    Next
    INDEX
    Explanations

    emoji

    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
    Not in Any Lists

    No Comments

    Negative Logits
    FlightID
    0.39
    ريح
    0.39
    ật
    0.39
    OGRAPHY
    0.38
    澳洲
    0.38
    테
    0.38
    椽
    0.38
    粹
    0.37
    ະ
    0.37
     Barron
    0.37
    POSITIVE LOGITS
     emoji
    1.09
     emojis
    1.08
     Emoji
    0.96
    Emoji
    0.95
    emoji
    0.95
    Emojis
    0.84
     emoticon
    0.68
     эмо
    0.60
    Emo
    0.55
     emotes
    0.55
    Activations Density 0.001%

    No Known Activations