Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4399
    Prev
    Next
    INDEX
    Explanations

    react component naming convention

    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
    থেষ্ট
    1.95
    }$(
    1.88
    岖
    1.77
    +}$
    1.72
    }\
    1.70
    возможно
    1.61
    imageNamed
    1.61
    vous
    1.61
    alumno
    1.59
     milled
    1.59
    POSITIVE LOGITS
    d
    2.02
     ç
    1.58
     ply
    1.58
    本社
    1.56
     kaya
    1.55
     sentiment
    1.53
    ڈی
    1.50
    reciation
    1.46
     sepak
    1.44
     pl
    1.44
    Activations Density 0.001%

    No Known Activations