© 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. 11509
    Prev
    Next
    INDEX
    Explanations

    references to plans, ways, or methods for doing something.

    oai_token-act-pair · gemini-2.0-flash

    Opportunities or ways of doing

    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
     dolci
    -0.34
    や
    -0.33
     alpina
    -0.33
    sqlQuery
    -0.32
    <bos>
    -0.32
    ütü
    -0.31
     algu
    -0.31
    ca
    -0.30
    elsif
    -0.29
    切
    -0.29
    POSITIVE LOGITS
     consume
    1.19
     solve
    1.17
     raise
    1.16
     allocate
    1.16
     marry
    1.15
     improve
    1.14
     decorate
    1.13
     protect
    1.13
     distribute
    1.13
     acquire
    1.12
    Activations Density 31.031%

    No Known Activations