© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11317
    Prev
    Next
    INDEX
    Explanations

    words related to light and vision and communication.

    oai_token-act-pair · gemini-2.0-flash

    light sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Rhestr
    -0.86
     propOrder
    -0.82
    Diwedd
    -0.81
    AndEndTag
    -0.80
    UnitTesting
    -0.78
    Autoritní
    -0.75
    ImageContext
    -0.74
     noDo
    -0.74
    ItemBackground
    -0.73
    PhysRev
    -0.73
    POSITIVE LOGITS
     bathing
    0.52
    a
    0.46
     a
    0.44
     Hawkins
    0.40
    ula
    0.40
    ði
    0.40
    یمت
    0.39
     war
    0.38
    rin
    0.38
    -
    0.38
    Activations Density 3.721%

    No Known Activations