© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12513
    Prev
    Next
    INDEX
    Explanations

    equation syntax, mathematical symbols, section labels, and other source code and mark-up artifacts.

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nemici
    -0.46
    He
    -0.43
     soldati
    -0.40
     popoli
    -0.38
     piú
    -0.38
     cuivre
    -0.38
    My
    -0.36
     irré
    -0.36
     potuto
    -0.36
    by
    -0.35
    POSITIVE LOGITS
    SEGUIR
    0.93
    insegna
    0.80
    Controllo
    0.78
    naphthal
    0.78
    hematical
    0.78
    Numerade
    0.78
    collana
    0.77
    ADRID
    0.76
    intenance
    0.75
     Shakspeare
    0.75
    Activations Density 18.332%

    No Known Activations