© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229374
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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_57_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
    Owing
    0.38
     Owing
    0.37
    તર
    0.37
     dist
    0.36
    culpa
    0.36
     owing
    0.36
     කර
    0.36
    ($"{
    0.36
    ipada
    0.35
     authored
    0.35
    POSITIVE LOGITS
     скло
    0.43
    __))
    0.37
     prévenir
    0.37
    ))))
    0.36
     membut
    0.35
     Locke
    0.35
     доказа
    0.35
    traces
    0.35
     ;\
    0.35
    过滤
    0.35
    Activations Density 0.004%

    No Known Activations