© 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
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 228795
    Prev
    Next
    INDEX
    Explanations

    you

    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
    ടങ്ങ
    0.40
     டீ
    0.38
    袂
    0.36
    kien
    0.36
    ணற
    0.36
    ruzione
    0.36
    reements
    0.35
    ensureEqual
    0.35
    HANG
    0.35
    dropPanel
    0.34
    POSITIVE LOGITS
     Prices
    0.48
     w
    0.47
     W
    0.44
     prices
    0.44
     Before
    0.42
     Price
    0.40
    Prices
    0.40
     Preise
    0.40
     before
    0.40
    人和
    0.40
    Activations Density 0.003%

    No Known Activations