© 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. 167010
    Prev
    Next
    INDEX
    Explanations

    prayer

    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
    σό
    0.38
     provisions
    0.38
     Investigations
    0.37
     அறி
    0.37
     Provisions
    0.37
     Corporate
    0.36
     monthly
    0.36
    適
    0.36
     daily
    0.36
    定期
    0.36
    POSITIVE LOGITS
     rug
    0.53
    book
    0.52
     rugs
    0.52
     book
    0.51
     Rug
    0.48
    dev
    0.45
     dev
    0.43
    rug
    0.43
    圈
    0.43
     বই
    0.42
    Activations Density 0.000%

    No Known Activations