© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10863
    Prev
    Next
    INDEX
    Explanations

    the contraction "I'm" and "we're"

    oai_token-act-pair · gemini-2.0-flash

    am/m

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Plan
    -0.45
    nene
    -0.43
     enum
    -0.43
     plan
    -0.42
    Mod
    -0.40
    шни
    -0.40
    sign
    -0.40
    duc
    -0.40
     Plan
    -0.40
    plan
    -0.39
    POSITIVE LOGITS
    ViewImports
    0.90
    ReusableCell
    0.84
    lapsingToolbar
    0.82
     للاسماء
    0.81
     surla
    0.80
    +#+#
    0.80
    клопе
    0.79
     незавершена
    0.78
     defaultstate
    0.78
    ParallelGroup
    0.77
    Activations Density 1.299%

    No Known Activations