© 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. 10091
    Prev
    Next
    INDEX
    Explanations

    scientific terms relating to objects measured on the micro and nano scale

    oai_token-act-pair · gemini-2.0-flash

    micro

    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
     micro
    -2.45
     Micro
    -2.23
    Micro
    -2.20
    micro
    -2.20
     MICRO
    -1.80
     mikro
    -1.67
    MICRO
    -1.62
     Mikro
    -1.52
     микро
    -1.45
    Mikro
    -1.44
    POSITIVE LOGITS
     незавершена
    0.62
    +#+#
    0.62
    LEn
    0.58
    __(/*!
    0.58
     дописавши
    0.54
    principalColumn
    0.54
    XmlAccessType
    0.54
    ettbewer
    0.54
    GEBURTS
    0.54
    featureID
    0.54
    Activations Density 9.282%

    No Known Activations