© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15170
    Prev
    Next
    INDEX
    Explanations

    technical documents describing the parts and function of mechanical devices

    oai_token-act-pair · gemini-2.0-flash

    terms related to positioning and movement

    np_token-act-pair-logits · gpt-4o-mini

    precise controlled movement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     henvisninger
    -0.68
     désolés
    -0.59
    WEBPACK
    -0.54
    wój
    -0.50
     réessayer
    -0.49
    ulp
    -0.49
     culturelles
    -0.48
    principalColumn
    -0.46
    providedIn
    -0.46
    SuppressMessage
    -0.44
    POSITIVE LOGITS
    positioning
    0.72
    Koordinaten
    0.71
     positioning
    0.69
     position
    0.67
     stage
    0.63
     move
    0.62
     Position
    0.62
    position
    0.61
    Transkript
    0.61
    stages
    0.59
    Activations Density 3.174%

    No Known Activations