© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1299
    Prev
    Next
    INDEX
    Explanations

    words related to shapes, measurements, and orientation, particularly horizontal and vertical

    oai_token-act-pair · gemini-2.0-flash

    vertical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     vertical
    -2.36
     horizontal
    -2.22
    vertical
    -2.09
     Vertical
    -2.05
    Vertical
    -2.00
    horizontal
    -1.93
     Horizontal
    -1.91
    Horizontal
    -1.86
     VERTICAL
    -1.75
     vertically
    -1.74
    POSITIVE LOGITS
    rungsseite
    0.84
    endphp
    0.79
    IntoConstraints
    0.79
     ExecuteAsync
    0.76
     дописавши
    0.75
    ViewFeatures
    0.74
     Exacts
    0.73
    queryInterface
    0.67
    unknownFields
    0.66
     calendriers
    0.65
    Activations Density 14.478%

    No Known Activations