© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10182
    Prev
    Next
    INDEX
    Explanations

    code-related tokens like function names and parameters

    oai_token-act-pair · gemini-2.0-flash

    parentheses and quotes

    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
    نی
    -0.17
    नि
    -0.17
     decentral
    -0.16
    ora
    -0.15
    de
    -0.15
    替
    -0.15
    änd
    -0.14
    Ecco
    -0.14
     شو
    -0.14
    on
    -0.13
    POSITIVE LOGITS
    ")
    1.49
    )
    1.41
    "),
    1.40
    "):
    1.37
    ")]
    1.37
    ')
    1.36
    ).
    1.33
    '),
    1.33
    ),
    1.30
    )");
    1.30
    Activations Density 25.276%

    No Known Activations