© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6003
    Prev
    Next
    INDEX
    Explanations

    punny phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    OCUS
    0.39
     Prima
    0.38
    铆
    0.38
    ಸ್ಕೊ
    0.37
    纬
    0.36
     abhiv
    0.36
     библиоте
    0.36
     afore
    0.36
    LLCATS
    0.35
     TikTok
    0.35
    POSITIVE LOGITS
    ༼
    0.46
     troll
    0.42
     trolling
    0.41
    TIL
    0.39
     obligatory
    0.39
    dat
    0.38
     ugu
    0.37
     deserving
    0.36
     holy
    0.36
     profit
    0.35
    Activations Density 0.179%

    No Known Activations