© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10581
    Prev
    Next
    INDEX
    Explanations

    mentions of standards, protocols, criteria, or canons in formal guidelines

    oai_token-act-pair · gemini-2.0-flash

    standard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     standard
    -2.67
    standard
    -2.44
     Standard
    -2.44
    Standard
    -2.42
     STANDARD
    -2.16
    STANDARD
    -2.16
     standards
    -2.02
     standaard
    -1.92
     estándar
    -1.91
    标准
    -1.90
    POSITIVE LOGITS
    SharedDtor
    0.70
    IntoConstraints
    0.69
    InjectAttribute
    0.63
    pherals
    0.58
    Спољашње
    0.55
    TargetException
    0.55
     <=",
    0.54
    béco
    0.53
     Италијани
    0.52
    TagHelper
    0.51
    Activations Density 2.937%

    No Known Activations