© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130412
    Prev
    Next
    INDEX
    Explanations

    say "ass"

    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_50_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
    <unused51>
    0.39
    ufen
    0.38
    ürü
    0.38
     Saber
    0.37
    영어
    0.36
    蛯
    0.36
    从业
    0.35
    𝓐
    0.34
     प्रो
    0.34
    ृ
    0.34
    POSITIVE LOGITS
    ass
    1.35
    Ass
    1.29
     ass
    1.26
     Ass
    1.19
    ASS
    1.15
     ASS
    1.11
    asses
    1.10
    assing
    1.02
    assa
    1.00
    asso
    0.94
    Activations Density 0.001%

    No Known Activations