© 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. 13820
    Prev
    Next
    INDEX
    Explanations

    code related to AngularJS controllers, scopes, and directives

    oai_token-act-pair · gemini-2.0-flash

    scope

    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
    scope
    -0.60
    scopes
    -0.57
     scopes
    -0.49
     respective
    -0.46
    PRNewswire
    -0.45
    databinding
    -0.43
     tkinter
    -0.42
    ilfe
    -0.42
    DJANGO
    -0.41
     SQLAlchemy
    -0.41
    POSITIVE LOGITS
    addPreferredGap
    0.91
     ]
    0.87
     kaarangay
    0.73
    DockStyle
    0.73
    AddHtmlAttribute
    0.73
    <bos>
    0.72
     صوتيه
    0.71
     comuniques
    0.70
     Himo
    0.69
    UnknownFieldSet
    0.69
    Activations Density 0.512%

    No Known Activations