© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6976
    Prev
    Next
    INDEX
    Explanations

    words referring to locations, families and species

    oai_token-act-pair · gemini-2.0-flash

    Technical/Academic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.54
     of
    -0.50
    médiaire
    -0.50
    seguida
    -0.50
    ensement
    -0.49
    NUMX
    -0.47
    XMLSchema
    -0.47
    ẾT
    -0.47
    rahat
    -0.47
    noons
    -0.46
    POSITIVE LOGITS
    AccessorTable
    0.58
     समीक्षक
    0.56
     initComponents
    0.52
    apimachinery
    0.52
    crollView
    0.49
     ri
    0.48
     الحره
    0.48
    ิม
    0.47
     виправивши
    0.47
     GenerationType
    0.47
    Activations Density 0.359%

    No Known Activations