© 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. 9132
    Prev
    Next
    INDEX
    Explanations

    client briefs

    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
     saluran
    0.69
     ép
    0.63
     दृढ़
    0.62
    υν
    0.61
     repulsion
    0.61
    কার্য
    0.60
     ağır
    0.59
    Ự
    0.59
    タップ
    0.59
    Purs
    0.58
    POSITIVE LOGITS
     client
    2.04
     briefs
    1.99
     Brief
    1.97
     brief
    1.96
     Client
    1.82
    client
    1.81
    Brief
    1.77
    brief
    1.77
    Client
    1.75
     clients
    1.75
    Activations Density 0.676%

    No Known Activations