© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177287
    Prev
    Next
    INDEX
    Explanations

    sin/sinister

    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
    tid
    0.38
    Geolocation
    0.37
    rary
    0.36
    ovanje
    0.36
     Neptune
    0.36
    മ
    0.35
     nowDate
    0.35
     tid
    0.34
    溟
    0.34
    Tcp
    0.34
    POSITIVE LOGITS
     Sin
    1.52
    Sin
    1.44
     sinister
    1.42
     SIN
    1.37
    sin
    1.35
    SIN
    1.31
     sin
    1.30
     dx
    1.27
     Dexter
    1.23
     DX
    1.23
    Activations Density 0.019%

    No Known Activations