© 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. 15453
    Prev
    Next
    INDEX
    Explanations

    words related to roads, pathways, and traffic

    oai_token-act-pair · gemini-2.0-flash

    warnings and prohibitions

    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
    SharedDtor
    -0.63
    Öffnungszeiten
    -0.61
    oneofs
    -0.60
    érience
    -0.59
    astify
    -0.58
    raires
    -0.57
    apunov
    -0.56
    TemporalType
    -0.55
    <bos>
    -0.55
    gbaar
    -0.54
    POSITIVE LOGITS
    ikor
    0.48
    =<?
    0.48
    Ծանոթ
    0.47
    Datuak
    0.47
    didSet
    0.45
    AutoScaleMode
    0.45
    /***/
    0.44
    contentLoaded
    0.44
     useDispatch
    0.43
    landi
    0.43
    Activations Density 8.042%

    No Known Activations