© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12810
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to eyes and vision

    oai_token-act-pair · gemini-2.0-flash

    eyes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     pubb
    -0.48
    bodies
    -0.45
     lobes
    -0.44
    SequentialGroup
    -0.44
    Cyfeiriadau
    -0.43
    扁
    -0.43
    QMetaType
    -0.43
     חיצוניים
    -0.42
    roms
    -0.42
    号
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.93
     समीक्षाओं
    0.84
     eye
    0.67
    ViewFeatures
    0.64
    posedge
    0.61
    tagHelperRunner
    0.60
     GenerationType
    0.59
     left
    0.59
    InSection
    0.59
    rawDesc
    0.58
    Activations Density 1.329%

    No Known Activations