© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13201
    Prev
    Next
    INDEX
    Explanations

    academic research writing about physics and math

    oai_token-act-pair · gemini-2.0-flash

    model

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -0.64
    '>";
    -0.62
    MENAFN
    -0.60
     Morrissey
    -0.59
     cdti
    -0.59
    --]
    -0.57
     Nebu
    -0.57
    ">',
    -0.56
     SPDX
    -0.56
    InstanceState
    -0.56
    POSITIVE LOGITS
     model
    0.61
     nakalista
    0.57
    ClientSize
    0.52
     models
    0.51
    model
    0.51
    rdag
    0.47
    XmlAccessorType
    0.47
     Model
    0.46
    Model
    0.46
    NameInMap
    0.46
    Activations Density 5.385%

    No Known Activations