© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15353
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate negation, management, or physical discomfort.

    oai_token-act-pair · gemini-2.0-flash

    code examples/negative constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     kids
    -0.66
     everybody
    -0.60
     Everybody
    -0.59
     somebody
    -0.59
    Everybody
    -0.55
     anybody
    -0.54
    Kids
    -0.53
     oprot
    -0.53
    Â
    -0.50
     Kids
    -0.50
    POSITIVE LOGITS
    NUMX
    0.97
    interopRequire
    0.73
    onViewCreated
    0.69
    rehensible
    0.68
    #
    0.67
     XNUMX
    0.66
    PullParser
    0.65
    XmlAccessorType
    0.64
    tyimages
    0.60
    momix
    0.59
    Activations Density 3.817%

    No Known Activations