© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12238
    Prev
    Next
    INDEX
    Explanations

    words relating to code and configuration, including enabling, disabling, and referring to words

    oai_token-act-pair · gemini-2.0-flash

    enable disable words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    %)$
    -0.84
     CreateTagHelper
    -0.79
    setVerticalGroup
    -0.78
    }\]
    -0.78
    mybatisplus
    -0.77
     ApiException
    -0.77
    ']")
    -0.72
    )–
    -0.71
    yntaxException
    -0.71
     ModelExpression
    -0.71
    POSITIVE LOGITS
     mė
    0.69
     Tatsache
    0.62
     ragazze
    0.57
     gând
    0.56
     desiderio
    0.56
     ragazzo
    0.56
     begge
    0.56
     popolo
    0.55
    eye
    0.54
    wyżs
    0.54
    Activations Density 0.323%

    No Known Activations