© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15837
    Prev
    Next
    INDEX
    Explanations

    code snippets, file paths, and references within programming and software contexts along with some French words.

    oai_token-act-pair · gemini-2.0-flash

    (

    np_max-act · gemini-2.0-flash

    (

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     handleSubmit
    -0.51
     [*]
    -0.50
    Bindings
    -0.50
     “
    -0.49
    etero
    -0.48
     …
    -0.48
     ...
    -0.48
    umel
    -0.46
    ArgsConstructor
    -0.46
    abase
    -0.46
    POSITIVE LOGITS
     myſelf
    1.14
     itſelf
    1.13
     uſed
    1.05
     Monfieur
    1.03
     Jefus
    1.01
     Houſe
    0.99
     Majefty
    0.98
    <bos>
    0.97
     poffe
    0.96
     Reſ
    0.96
    Activations Density 5.479%

    No Known Activations