© 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. 6871
    Prev
    Next
    INDEX
    Explanations

    the start of XML/HTML code blocks and/or short words connecting statements together

    oai_token-act-pair · 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
     CBD
    -1.06
     PM
    -1.00
     CSS
    -0.99
     RPC
    -0.99
     CG
    -0.97
     PC
    -0.97
     getID
    -0.96
     SSD
    -0.94
     APA
    -0.93
     OS
    -0.92
    POSITIVE LOGITS
    InSection
    0.41
     juges
    0.40
    StoreMessageInfo
    0.39
     visibilité
    0.39
     loisirs
    0.39
    FRAGMENT
    0.38
     crainte
    0.38
    BINARY
    0.38
     rempliss
    0.37
    VALIDATION
    0.37
    Activations Density 4.582%

    No Known Activations