© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11953
    Prev
    Next
    INDEX
    Explanations

    words related to a language other than English and the phrase "forded by" or "forded an"

    oai_token-act-pair · gemini-2.0-flash

    legal/policy texts

    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
     CreateTagHelper
    -0.89
     ModelExpression
    -0.69
    onAttach
    -0.67
     مشين
    -0.66
     صوتيه
    -0.64
    abestanden
    -0.64
    Nazionale
    -0.63
    XmlEnum
    -0.63
     Roskov
    -0.62
    ArgsConstructor
    -0.62
    POSITIVE LOGITS
     provides
    0.75
    provides
    0.72
     Provides
    0.69
     providing
    0.69
     Providing
    0.68
    Providing
    0.67
     offers
    0.66
     provided
    0.65
     provide
    0.65
    offers
    0.64
    Activations Density 0.473%

    No Known Activations