© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3561
    Prev
    Next
    INDEX
    Explanations

    dialogue markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ад
    1.13
     불구하고
    1.12
    昛
    1.08
    night
    1.08
    forRoot
    1.04
    Traditionally
    1.04
    拃
    1.03
    efined
    1.03
    üü
    1.02
    担当
    1.02
    POSITIVE LOGITS
    ς
    1.26
     dà
    1.21
     vy
    1.17
    celain
    1.16
    s
    1.09
    来说
    1.09
    t
    1.07
    いう
    1.05
     וא
    1.04
    sib
    1.02
    Activations Density 0.014%

    No Known Activations