© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2991
    Prev
    Next
    INDEX
    Explanations

    the Spanish language and programming terms

    oai_token-act-pair · gemini-2.0-flash

    mixed languages and code

    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
    PRNewswire
    -0.74
    WebVitals
    -0.64
    Tikang
    -0.61
     ModelExpression
    -0.57
    */),
    -0.55
     dàng
    -0.55
    HasAnnotation
    -0.54
    webElementGuid
    -0.54
    ahrt
    -0.53
    ГЛА
    -0.53
    POSITIVE LOGITS
    XmlAccessType
    0.51
     préc
    0.48
    nos
    0.45
     professionali
    0.44
     alimentaire
    0.44
     fumée
    0.43
    se
    0.43
     tecnici
    0.42
    insegna
    0.42
     firebaseConfig
    0.42
    Activations Density 1.113%

    No Known Activations