© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9104
    Prev
    Next
    INDEX
    Explanations

    body

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     browser
    0.80
     сала
    0.75
     ASCII
    0.71
    扰
    0.71
    webkit
    0.70
    irmi
    0.69
     Wiggins
    0.69
     брау
    0.68
    翁
    0.67
    锹
    0.66
    POSITIVE LOGITS
     deceleration
    0.61
     ul
    0.60
     身
    0.60
     body
    0.59
     transfer
    0.59
    Landing
    0.58
    connect
    0.58
     cycl
    0.57
    Body
    0.56
     Landing
    0.56
    Activations Density 0.003%

    No Known Activations