© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3948
    Prev
    Next
    INDEX
    Explanations

    scientific or research documents relating to health, safety, or fuels

    oai_token-act-pair · gemini-2.0-flash

    international agreements/regulations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    INSIDE
    -0.50
    ])));
    -0.47
    yoo
    -0.47
     lenker
    -0.45
     Quir
    -0.45
     adjournment
    -0.45
    stylesheet
    -0.43
     múl
    -0.42
    క్ష
    -0.41
     ब्रेकडाउन
    -0.41
    POSITIVE LOGITS
    UnsafeEnabled
    0.66
    AddTagHelper
    0.62
    Obrázky
    0.60
    MessageTagHelper
    0.59
    ="@+
    0.57
    OwnProperty
    0.56
    Brainz
    0.55
    ulsory
    0.54
    MergeFrom
    0.54
     typelib
    0.54
    Activations Density 3.319%

    No Known Activations