© 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. 12516
    Prev
    Next
    INDEX
    Explanations

    passages discussing guidelines, protection or safety measures, alongside related advice or information.

    oai_token-act-pair · gemini-2.0-flash

    preventative measures

    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
     كومونز
    -0.69
     InputDecoration
    -0.63
    ."</
    -0.60
     BrowserModule
    -0.58
    GeneratedValue
    -0.57
     setType
    -0.57
    bable
    -0.56
    })()
    -0.55
    resave
    -0.54
     useStyles
    -0.53
    POSITIVE LOGITS
     المعيارى
    0.56
    nsito
    0.49
    neté
    0.47
    SharedDtor
    0.46
    opsida
    0.45
    XmlType
    0.45
    legi
    0.45
    ASA
    0.45
    hada
    0.44
    kenn
    0.44
    Activations Density 1.962%

    No Known Activations