© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141595
    Prev
    Next
    INDEX
    Explanations

    show or speak

    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_46_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
    ोदय
    0.51
     grab
    0.39
    Pick
    0.38
     brengen
    0.38
     grabbing
    0.38
    getState
    0.37
     င
    0.37
     Pick
    0.37
     가져
    0.37
    买
    0.37
    POSITIVE LOGITS
    SHOW
    0.46
    show
    0.45
     berbicara
    0.44
     habla
    0.43
     hablando
    0.42
    CHANT
    0.41
     চেক
    0.39
     show
    0.39
    Checking
    0.38
     fala
    0.38
    Activations Density 0.046%

    No Known Activations