© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3073
    Prev
    Next
    INDEX
    Explanations

    verbs relating to taking action

    oai_token-act-pair · gemini-2.0-flash

    advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    wikidata
    -0.64
    Filmografie
    -0.55
    setViewportView
    -0.54
    /******/
    -0.50
     متحده
    -0.50
     يتيمه
    -0.47
     ModelExpression
    -0.46
    Spoljašnje
    -0.46
     ***!
    -0.46
    Skocz
    -0.46
    POSITIVE LOGITS
     opportunistic
    0.61
    aliyun
    0.59
    BlockPos
    0.57
    ArrowToggle
    0.53
     "..\..\..\
    0.52
     slotted
    0.50
    хьтан
    0.50
    awarkan
    0.50
     שוליים
    0.50
     exploiting
    0.50
    Activations Density 0.714%

    No Known Activations