© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167147
    Prev
    Next
    INDEX
    Explanations

    having

    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
    梵
    0.40
     অবস
    0.37
    ﹀
    0.36
    ቫ
    0.36
    emics
    0.36
    顶部
    0.36
    変化
    0.35
    ﹂
    0.35
    ishy
    0.34
    회사
    0.34
    POSITIVE LOGITS
    紧
    0.48
     tighter
    0.45
     ach
    0.44
     neck
    0.44
     tighten
    0.44
    indows
    0.44
     knee
    0.43
     wi
    0.43
     Wi
    0.43
     thicker
    0.43
    Activations Density 0.003%

    No Known Activations