© 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. 12906
    Prev
    Next
    INDEX
    Explanations

    legal or regulatory documents, references, and quotations within text.

    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
     Efq
    -0.86
     becauſe
    -0.76
     raiſ
    -0.75
     themſelves
    -0.74
     whoſe
    -0.73
     himſelf
    -0.73
     Houſe
    -0.73
     myſelf
    -0.73
     ſta
    -0.73
     ſhe
    -0.73
    POSITIVE LOGITS
     Matter
    0.44
    Handlung
    0.40
     Den
    0.37
     Ent
    0.37
     Cul
    0.37
     Point
    0.36
     Mis
    0.36
    >{@
    0.35
    kti
    0.35
     Cont
    0.35
    Activations Density 6.434%

    No Known Activations