© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10747
    Prev
    Next
    INDEX
    Explanations

    code related to menu asset order constants

    oai_token-act-pair · gemini-2.0-flash

    code related

    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
     مشين
    -0.61
    ^(@)
    -0.60
    leſs
    -0.60
    RenderAtEndOf
    -0.60
    ſhip
    -0.58
    wiſe
    -0.56
     iſt
    -0.55
    ientras
    -0.54
    Enllaces
    -0.53
     समीक्षाओं
    -0.53
    POSITIVE LOGITS
    SUFFIX
    0.44
    ENABLED
    0.44
    ENDPOINT
    0.44
    ENCODING
    0.42
     Xunit
    0.42
    ENUM
    0.42
    ATTRIBUTE
    0.41
    ENCOD
    0.40
    ARRAY
    0.40
    HANDLER
    0.39
    Activations Density 7.269%

    No Known Activations