© 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. 228715
    Prev
    Next
    INDEX
    Explanations

    numbers BBC News

    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
    k
    0.43
    bro
    0.41
    éra
    0.41
    di
    0.40
     Ultim
    0.39
    vi
    0.39
    셨
    0.38
    ny
    0.38
    nom
    0.38
    Dor
    0.38
    POSITIVE LOGITS
     oe
    0.46
     теле
    0.39
     seventeen
    0.39
    ००
    0.38
    வராக
    0.38
     cua
    0.38
     tele
    0.37
    WillAppear
    0.37
     BOOL
    0.37
    ھار
    0.37
    Activations Density 0.001%

    No Known Activations