© 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. 778
    Prev
    Next
    INDEX
    Explanations

    content in emails or code with punctuation and special characters

    oai_token-act-pair · gemini-2.0-flash

    Text fragments

    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
    릅
    -0.57
     hígado
    -0.52
     intestino
    -0.52
    purl
    -0.51
     He
    -0.50
     ujednoznacz
    -0.50
     cráneo
    -0.50
    ValueStyle
    -0.49
    elemField
    -0.49
     vérit
    -0.48
    POSITIVE LOGITS
    <bos>
    0.53
    .},
    0.52
    PROLOG
    0.51
    AutoScaleMode
    0.51
     tabletop
    0.50
    Ở
    0.49
    ∴
    0.49
    HttpFoundation
    0.49
    Referências
    0.48
    期刊论文
    0.48
    Activations Density 9.072%

    No Known Activations