© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2994
    Prev
    Next
    INDEX
    Explanations

    image analysis procedures and the parameters and timing of each procedure

    oai_token-act-pair · gemini-2.0-flash

    MRI data analysis

    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
    Negative Logits
    __':
    -0.57
     JpaRepository
    -0.52
    __':
    -0.50
    Шаг
    -0.46
    +#+#
    -0.45
     dost
    -0.44
    مصادر
    -0.43
    multicolumn
    -0.42
    Step
    -0.42
     joaat
    -0.42
    POSITIVE LOGITS
     noqa
    0.68
    awtextra
    0.63
    relativeTime
    0.59
     fielding
    0.59
    hyrchwyd
    0.59
     Мексичка
    0.58
     yyl
    0.58
     vengan
    0.56
     esternos
    0.56
     AssemblyTitle
    0.55
    Activations Density 4.290%

    No Known Activations