© 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. 15707
    Prev
    Next
    INDEX
    Explanations

    URLs, especially those with query parameters

    oai_token-act-pair · gemini-2.0-flash

    URLs or 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
     Económica
    -0.69
     Púb
    -0.67
     Pública
    -0.65
     EconPapers
    -0.62
     Мексичка
    -0.62
    SharedCtor
    -0.57
     Reſ
    -0.56
     Profesional
    -0.54
    MENAFN
    -0.54
     Públicas
    -0.54
    POSITIVE LOGITS
    %
    0.52
    )».
    0.50
    %).
    0.50
    =’
    0.50
    ="'.$
    0.50
    featureID
    0.49
    msgTypes
    0.48
    =%
    0.47
    })]
    0.47
    =";
    0.47
    Activations Density 18.611%

    No Known Activations