© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4610
    Prev
    Next
    INDEX
    Explanations

    ordinals and words associated with sequences

    oai_token-act-pair · gemini-2.0-flash

    things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ModelSerializer
    -0.44
    UIViewController
    -0.42
    Santis
    -0.40
    FilterChain
    -0.39
    Ecotoxicity
    -0.39
    TProtocol
    -0.37
     he
    -0.37
     espar
    -0.36
    っていますが
    -0.36
     ע
    -0.35
    POSITIVE LOGITS
     things
    2.17
     thing
    2.13
     Things
    1.89
    Things
    1.82
    things
    1.81
     THINGS
    1.77
     anything
    1.74
    thing
    1.72
     something
    1.70
     THING
    1.68
    Activations Density 1.859%

    No Known Activations