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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7267
    Prev
    Next
    INDEX
    Explanations

    code snippets and file paths

    oai_token-act-pair · gemini-2.0-flash

    copy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ValueStyle
    -0.73
    oredCriteria
    -0.67
    BufferException
    -0.59
     Exteriores
    -0.58
     وتسجيلات
    -0.58
     Reverso
    -0.57
    onOptions
    -0.57
     NSCoder
    -0.57
    avond
    -0.57
    FormState
    -0.57
    POSITIVE LOGITS
     copy
    0.54
    copy
    0.54
     Copy
    0.53
     COPY
    0.50
    copyTo
    0.48
    Copy
    0.47
     コピー
    0.46
     Rename
    0.45
     Cre
    0.44
    GeneratedMessage
    0.44
    Activations Density 1.889%

    No Known Activations