© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158124
    Prev
    Next
    INDEX
    Explanations

    seen

    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
     op
    0.40
    ﮅ
    0.40
    Op
    0.38
     Dogg
    0.38
    "{
    0.38
     Op
    0.36
    avk
    0.36
    AK
    0.35
    狗
    0.35
     ಕೂದಲ
    0.34
    POSITIVE LOGITS
     seen
    1.14
    seen
    1.12
     visto
    1.04
    Seen
    0.99
     Seen
    0.97
     gesehen
    0.77
     vistos
    0.77
     دیده
    0.68
    見
    0.68
     gezien
    0.66
    Activations Density 0.022%

    No Known Activations