© 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. 14778
    Prev
    Next
    INDEX
    Explanations

    phrases about a need for or the possibility of improvement

    oai_token-act-pair · gemini-2.0-flash

    Actions, needs, and improvements

    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
    initializeApp
    -0.82
    GraphicsUnit
    -0.79
    httphttps
    -0.78
    createCanvas
    -0.78
     ProtoMessage
    -0.75
    ViewFeatures
    -0.74
     indisponible
    -0.71
    \}\\
    -0.71
    Šaltiniai
    -0.71
     Exactos
    -0.71
    POSITIVE LOGITS
     need
    0.79
    need
    0.64
     needs
    0.63
    Need
    0.62
     Need
    0.60
    Needs
    0.58
     NEED
    0.57
    <bos>
    0.54
     needed
    0.52
     urgently
    0.49
    Activations Density 1.159%

    No Known Activations