© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7474
    Prev
    Next
    INDEX
    Explanations

    extracts of code

    oai_token-act-pair · gemini-2.0-flash

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ↵↵
    -0.50
    ↵
    -0.43
    __":
    -0.42
    __':
    -0.42
    permitAll
    -0.39
    mentos
    -0.39
    مكن
    -0.39
     jorden
    -0.38
     сър
    -0.36
    ingual
    -0.35
    POSITIVE LOGITS
    ScopeManager
    0.88
    +#+#
    0.84
     Италијани
    0.78
    NameInMap
    0.74
    httphttps
    0.72
    Hentet
    0.71
    webElement
    0.71
     BoxDecoration
    0.70
     ')[
    0.70
     CURLOPT
    0.69
    Activations Density 0.566%

    No Known Activations