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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 9258
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_31_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
     Serialization
    0.70
    ReturnValue
    0.64
     Entries
    0.64
    滃
    0.62
    avings
    0.62
     ܠ
    0.62
    ValueChanged
    0.60
    াক্রমে
    0.60
    นาด
    0.60
    잣
    0.59
    POSITIVE LOGITS
     Facultad
    0.67
     curso
    0.65
     nim
    0.64
    કાર
    0.63
     QB
    0.62
    蔡
    0.62
    aps
    0.62
    जो
    0.62
     Kurs
    0.61
     Eugene
    0.61
    Activations Density 0.000%

    No Known Activations