Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167354
    Prev
    Next
    INDEX
    Explanations

    auditions and applications

    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_56_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
    面
    1.38
     면
    1.33
    面的
    1.08
    면
    1.02
    的面
    0.95
    面上
    0.95
    面の
    0.93
    면에
    0.89
     面
    0.89
    面に
    0.83
    POSITIVE LOGITS
     audition
    1.81
     auditions
    1.60
     Bewer
    0.69
     Aud
    0.59
    采访
    0.57
    面试
    0.54
     Applicants
    0.54
     aud
    0.53
     audit
    0.53
     applicants
    0.52
    Activations Density 0.000%

    No Known Activations