© 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. 178241
    Prev
    Next
    INDEX
    Explanations

    video game content

    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
    Vir
    0.46
     Dracula
    0.43
     Sergi
    0.41
    vir
    0.40
     görül
    0.40
     सौरभ
    0.39
     Rö
    0.39
    夸
    0.38
     Saur
    0.38
    गंध
    0.38
    POSITIVE LOGITS
    ッズ
    0.42
    koliko
    0.40
     الك
    0.38
    ଳ
    0.38
     K
    0.38
    嗟
    0.37
    <iframe>
    0.36
     adequately
    0.36
     Valid
    0.36
    <tfoot>
    0.36
    Activations Density 0.000%

    No Known Activations