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. 167449
    Prev
    Next
    INDEX
    Explanations

    5

    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
    ettivi
    0.38
     GA
    0.35
    愔
    0.35
    ంగ
    0.35
    cA
    0.35
    উ
    0.35
    )=>{
    0.35
    ர்வ
    0.34
    overview
    0.33
    ொரு
    0.33
    POSITIVE LOGITS
    Attached
    0.52
    quote
    0.46
    Quote
    0.44
     Attached
    0.44
     Deleted
    0.42
    Deleted
    0.40
    Originally
    0.40
    ']
    0.39
     quote
    0.37
     Originally
    0.36
    Activations Density 0.000%

    No Known Activations