© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5451
    Prev
    Next
    INDEX
    Explanations

    Wi-Fi

    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_3_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
    Σ
    2.93
    ता
    2.85
    ſt
    2.84
    ेशन
    2.83
    astly
    2.81
    dana
    2.80
    রুখ
    2.79
    ர்
    2.69
    dür
    2.69
    r
    2.60
    POSITIVE LOGITS
    й
    3.13
    情况下
    2.79
    이번
    2.55
    мо
    2.38
    ؘ
    2.32
     nombres
    2.25
     cuarent
    2.24
     সাথে
    2.23
     pedidos
    2.19
    ので
    2.18
    Activations Density 0.025%

    No Known Activations