© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2022
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related terms such as public, static, string, set, get, and class

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    a
    -1.35
    in
    -1.26
    e
    -1.16
    A
    -1.16
    on
    -1.16
    as
    -1.15
    v
    -1.15
    for
    -1.14
    if
    -1.12
    h
    -1.12
    POSITIVE LOGITS
    ricultural
    0.86
    ecutive
    0.79
    othesis
    0.78
    encils
    0.77
    haviour
    0.77
    frastructure
    0.76
    ipheral
    0.76
    ratulations
    0.75
    hematical
    0.75
    ercises
    0.75
    Activations Density 2.130%

    No Known Activations