© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32999
    Prev
    Next
    INDEX
    Explanations

    Kubernetes `apiVersion`

    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_31_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
     صنایع
    0.38
    ("[%
    0.35
    طلاع
    0.35
    fprintf
    0.34
    ']],
    0.34
    drá
    0.33
     ",",
    0.33
    发电
    0.33
    Opacity
    0.33
    beqz
    0.33
    POSITIVE LOGITS
     endomet
    0.49
     Storia
    0.43
     mod
    0.42
     morphology
    0.41
     Frau
    0.39
     岩
    0.39
     Historia
    0.38
     manuscripts
    0.38
     khel
    0.38
     Marzo
    0.38
    Activations Density 0.001%

    No Known Activations