© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91274
    Prev
    Next
    INDEX
    Explanations

    direct speech punctuation

    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_11_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
    AE
    0.46
    VENTORY
    0.46
    G
    0.44
     Studien
    0.42
    AF
    0.42
     médica
    0.42
    ER
    0.41
     Besonder
    0.41
    Medico
    0.41
    Chelsea
    0.41
    POSITIVE LOGITS
     in
    0.49
     plasmas
    0.48
     l
    0.48
    可以
    0.46
     eighties
    0.45
     glass
    0.44
     enl
    0.44
    zado
    0.43
     outbursts
    0.43
     iron
    0.43
    Activations Density 0.068%

    No Known Activations