© 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. 3581
    Prev
    Next
    INDEX
    Explanations

    already, install

    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
    ărat
    0.87
    აც
    0.85
    inck
    0.81
     ஏற்ப
    0.77
     Ведь
    0.77
     Combining
    0.77
    ﺪ
    0.76
     Prescription
    0.75
     cariño
    0.74
    শুধু
    0.74
    POSITIVE LOGITS
    d
    0.89
    স্বর
    0.81
    speople
    0.81
     불구하고
    0.74
    −
    0.73
    dh
    0.71
    leans
    0.71
    dn
    0.70
    ef
    0.68
    gehend
    0.67
    Activations Density 0.002%

    No Known Activations