© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4354
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming classes, methods and models

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     to
    -0.82
     e
    -0.74
     
    -0.73
     col
    -0.72
     La
    -0.71
     u
    -0.69
     set
    -0.68
     ber
    -0.68
     la
    -0.67
     a
    -0.66
    POSITIVE LOGITS
     nakalista
    1.30
     myſelf
    1.24
     greateſt
    1.13
     photolibrary
    1.13
     Houſe
    1.11
     Jefus
    1.11
     purpoſe
    1.11
     Reſ
    1.09
     Etrus
    1.09
     Anſ
    1.08
    Activations Density 1.890%

    No Known Activations