© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13751
    Prev
    Next
    INDEX
    Explanations

    code snippets including angle brackets, parentheses, and the word 'error'

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     RO
    -0.95
     JO
    -0.93
     LO
    -0.93
    LO
    -0.92
    jo
    -0.88
    RO
    -0.88
    IO
    -0.88
     ZO
    -0.88
    ZO
    -0.88
     BO
    -0.88
    POSITIVE LOGITS
    matitis
    0.54
    AsUp
    0.52
     Harlan
    0.51
    ilane
    0.49
    ReusableCell
    0.47
    IntentFilter
    0.45
     AttributeSet
    0.45
    thmus
    0.45
    icitis
    0.45
     MADRID
    0.44
    Activations Density 0.999%

    No Known Activations