© 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. 11704
    Prev
    Next
    INDEX
    Explanations

    the word "pure"

    oai_token-act-pair · gemini-2.0-flash

    pure

    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
     itſelf
    -0.99
     poffible
    -0.89
     fhort
    -0.85
     Efq
    -0.83
    tersebut
    -0.82
     Monfieur
    -0.79
     Majefty
    -0.78
     vanske
    -0.77
     ſeveral
    -0.75
     fevere
    -0.74
    POSITIVE LOGITS
    IGraphics
    0.69
    StoreMessageInfo
    0.68
    intree
    0.64
    最快更新
    0.61
     BoxDecoration
    0.61
     Truss
    0.61
    </thead>
    0.60
    PropertyChanging
    0.60
    rinfo
    0.59
    ******/
    0.59
    Activations Density 1.047%

    No Known Activations