© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176502
    Prev
    Next
    INDEX
    Explanations

    code constructs

    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_24_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
     Alessandro
    0.50
     lees
    0.42
     g
    0.40
     solns
    0.39
     l
    0.39
     ro
    0.38
     remit
    0.38
    ENES
    0.37
    ည့်
    0.37
    glRasterPos
    0.37
    POSITIVE LOGITS
    ди
    0.42
    精彩
    0.41
    㚅
    0.41
     случае
    0.41
     concluded
    0.40
    ógicos
    0.40
    バック
    0.39
     காரணம்
    0.39
    conferences
    0.39
    侧
    0.39
    Activations Density 0.000%

    No Known Activations