© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10936
    Prev
    Next
    INDEX
    Explanations

    the word "focus" and words related to focusing an image.

    oai_token-act-pair · gemini-2.0-flash

    focus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    kan
    -1.02
    KAN
    -0.88
     kan
    -0.82
     focus
    -0.72
     Kan
    -0.63
    Kan
    -0.61
     KAN
    -0.60
    focus
    -0.57
     Focus
    -0.56
    кан
    -0.54
    POSITIVE LOGITS
    CrossRef
    0.79
    enumi
    0.73
     متعلقه
    0.71
    ecore
    0.66
    Bibliograf
    0.63
    ByExample
    0.62
    setupUi
    0.60
    +#+#
    0.59
     оригіналу
    0.57
    MigrationBuilder
    0.57
    Activations Density 0.731%

    No Known Activations