© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138088
    Prev
    Next
    INDEX
    Explanations

    shapesforma

    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_12_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
     HTML
    0.54
     <
    0.53
     શ
    0.53
    痪
    0.52
     quarrel
    0.49
     samano
    0.49
     PVC
    0.49
     Teaching
    0.48
    ક
    0.48
     된다
    0.48
    POSITIVE LOGITS
    ucar
    0.55
    ineri
    0.48
    ULAR
    0.47
    cap
    0.45
    xc
    0.45
     postul
    0.45
     '&
    0.45
    читы
    0.45
    AL
    0.44
    seti
    0.44
    Activations Density 0.024%

    No Known Activations