© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16203
    Prev
    Next
    INDEX
    Explanations

    horizontal lines and code snippets

    oai_token-act-pair · gemini-2.0-flash

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ----------------
    -0.58
    jLabel
    -0.50
     venons
    -0.47
    తు
    -0.47
    XmlAccessorType
    -0.46
    onatos
    -0.46
     andato
    -0.45
    ================
    -0.44
    ----------
    -0.43
    ami
    -0.43
    POSITIVE LOGITS
    sidemargin
    0.92
     Baillargeon
    0.77
     ostavi
    0.74
    SPATH
    0.73
     мәкал
    0.68
    الحياه
    0.65
    StructEnd
    0.65
    الإنجليزية
    0.65
    DoubleQuotes
    0.63
    
    0.63
    Activations Density 16.067%

    No Known Activations