© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14429
    Prev
    Next
    INDEX
    Explanations

    snippets of code, locations, and verbs ending in "ing"

    oai_token-act-pair · gemini-2.0-flash

    Illinois

    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
     IL
    -1.88
     Ill
    -1.81
     Illinois
    -1.80
     Il
    -1.71
     il
    -1.66
    Illinois
    -1.64
     ILL
    -1.63
     ill
    -1.59
     Chicago
    -1.58
    Il
    -1.52
    POSITIVE LOGITS
     GenerationType
    0.69
    +#+#
    0.66
     المعيارى
    0.57
    Билгалдахарш
    0.56
     estekak
    0.56
    ملكة
    0.55
     PCM
    0.55
     الرياضيه
    0.52
     ProtoMessage
    0.52
     Rumuni
    0.50
    Activations Density 1.576%

    No Known Activations