© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3768
    Prev
    Next
    INDEX
    Explanations

    facebook developer platform

    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
    மாவ
    0.41
     …..
    0.41
     fouls
    0.40
     !!!!!
    0.38
    ebok
    0.38
    ELIST
    0.38
     geslacht
    0.38
    ଆ
    0.38
    elist
    0.37
    สเตอร์
    0.37
    POSITIVE LOGITS
    getTargetContext
    0.38
    paque
    0.36
     Adri
    0.35
     Connectivity
    0.35
    MPC
    0.35
    GC
    0.34
     dat
    0.34
     WebDriver
    0.33
     suburban
    0.33
    integr
    0.32
    Activations Density 0.008%

    No Known Activations