© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8360
    Prev
    Next
    INDEX
    Explanations

    comments and code snippets related to licenses and copyright

    oai_token-act-pair · gemini-2.0-flash

    Code and licensing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     in
    -1.00
     as
    -0.99
     with
    -0.79
    with
    -0.71
    as
    -0.70
     for
    -0.68
     
    -0.66
    for
    -0.66
     a
    -0.65
     With
    -0.65
    POSITIVE LOGITS
     Efq
    1.54
     itſelf
    1.34
     Theſe
    1.34
     Monfieur
    1.34
     Jefus
    1.33
     myſelf
    1.29
     Shakspeare
    1.21
     ་་
    1.21
     doubtnut
    1.18
     iſt
    1.17
    Activations Density 14.195%

    No Known Activations