© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5105
    Prev
    Next
    INDEX
    Explanations

    a mix of words in Russian and code-related terms (possibly file extensions or functions), along with common English conjunctions and prepositions

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
     Executors
    -0.32
     EClass
    -0.32
     @"/
    -0.30
    rentices
    -0.29
    cibles
    -0.29
    parsedMessage
    -0.28
     pauper
    -0.28
     pedestal
    -0.28
     Fides
    -0.27
     Astral
    -0.27
    POSITIVE LOGITS
     quæ
    1.12
     auffi
    1.05
     purpoſe
    1.02
     houſe
    1.02
     Efq
    1.01
     ainfi
    1.01
     ſch
    0.96
     Eſ
    0.95
     ſeveral
    0.95
     ſta
    0.95
    Activations Density 0.354%

    No Known Activations