© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14718
    Prev
    Next
    INDEX
    Explanations

    lines of characters that form long separators, likely for comments in code

    oai_token-act-pair · gemini-2.0-flash

    Horizontal lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    LEncoder
    -0.81
    hyrchwyd
    -0.73
    ázaro
    -0.70
     isInitialized
    -0.69
    ειτουργ
    -0.67
    AsUp
    -0.65
    DockStyle
    -0.64
     насељу
    -0.63
     tartalomajánló
    -0.63
     StringTokenizer
    -0.61
    POSITIVE LOGITS
    CloseOperation
    0.45
    Bronnen
    0.44
     term
    0.44
    IsContent
    0.44
    Term
    0.43
     بيان
    0.40
    Terms
    0.40
     términos
    0.40
     Term
    0.40
     pus
    0.39
    Activations Density 0.189%

    No Known Activations