© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6348
    Prev
    Next
    INDEX
    Explanations

    abstract ideas, especially in the context of research papers

    oai_token-act-pair · gemini-2.0-flash

    processes and actions

    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
    RenderAtEndOf
    -0.82
     reaſon
    -0.81
     ſind
    -0.70
     uſed
    -0.70
     poffible
    -0.69
     themſelves
    -0.68
     Efq
    -0.68
     Anſ
    -0.67
     Conſ
    -0.66
     Theſe
    -0.66
    POSITIVE LOGITS
     together
    0.60
    together
    0.54
     within
    0.52
    twimg
    0.51
     base
    0.48
     eng
    0.48
     side
    0.48
     on
    0.47
    bas
    0.47
    Together
    0.47
    Activations Density 3.451%

    No Known Activations