© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241776
    Prev
    Next
    INDEX
    Explanations

    face value or strike price

    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_25_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
    ,{\
    0.41
    
    0.40
     ordinances
    0.38
    ؕ
    0.37
    appid
    0.37
     festivities
    0.37
     Majors
    0.37
     rich
    0.36
     fasse
    0.36
     explique
    0.36
    POSITIVE LOGITS
     सेवाएं
    0.40
    乃
    0.39
     izango
    0.38
     대상으로
    0.38
    <unused1016>
    0.37
    她在
    0.36
     रखरखाव
    0.36
     şimdi
    0.36
     освобо
    0.36
     тря
    0.36
    Activations Density 0.002%

    No Known Activations