© 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. 7353
    Prev
    Next
    INDEX
    Explanations

    numbered lists or dates

    oai_token-act-pair · gemini-2.0-flash

    code or errors

    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
    CodedInputStream
    -0.79
    RenderAtEndOf
    -0.75
     '{@
    -0.72
    帖最后由
    -0.69
    IsMutable
    -0.69
     beginnetje
    -0.68
     typelib
    -0.68
     noqa
    -0.67
    DoubleQuotes
    -0.66
    انيف
    -0.66
    POSITIVE LOGITS
    MemoryWarning
    0.61
    °
    0.41
    queryInterface
    0.41
    ritation
    0.40
    abonnement
    0.38
    #+#
    0.37
     Rig
    0.37
    tetten
    0.36
    e
    0.36
     ägg
    0.36
    Activations Density 1.424%

    No Known Activations