© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199752
    Prev
    Next
    INDEX
    Explanations

    say "ap" words

    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_50_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
     trúc
    0.38
     पाठ्यक्रम
    0.37
    omal
    0.37
     Roger
    0.36
     Parl
    0.36
    NaCl
    0.36
     сал
    0.36
    ታ
    0.36
    Ingredients
    0.34
     전달
    0.34
    POSITIVE LOGITS
     Ano
    0.44
     stripper
    0.42
    gged
    0.41
    ordinated
    0.40
    aked
    0.40
    aded
    0.40
    oggled
    0.40
    otted
    0.39
    amano
    0.38
     johnson
    0.38
    Activations Density 0.000%

    No Known Activations