© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10140
    Prev
    Next
    INDEX
    Explanations

    HTML or source code markup

    oai_token-act-pair · gemini-2.0-flash

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    '))
    -0.54
     ***!
    -0.54
    */),
    -0.52
    éri
    -0.50
    ณ
    -0.48
     Vikipedi
    -0.47
    HostException
    -0.47
     Polda
    -0.47
    ">)</
    -0.47
    >())
    -0.47
    POSITIVE LOGITS
    PerformLayout
    0.68
     EconPapers
    0.65
    GEBURTSDATUM
    0.58
     Normdatei
    0.57
     الحره
    0.57
    ResumeLayout
    0.55
    Демографія
    0.54
    muerzo
    0.52
     lenker
    0.50
    fastjson
    0.50
    Activations Density 9.899%

    No Known Activations