© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12915
    Prev
    Next
    INDEX
    Explanations

    uncommon characters, place names starting with "Š", and numerical lists in itemized form.

    oai_token-act-pair · gemini-2.0-flash

    Dashes

    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
     ín
    -0.72
     decât
    -0.72
     Māori
    -0.71
     leído
    -0.71
    oltà
    -0.70
     coö
    -0.68
     În
    -0.68
     Américas
    -0.67
     caractères
    -0.66
     MÉXICO
    -0.66
    POSITIVE LOGITS
     --
    0.69
     __
    0.55
    --
    0.46
    ――
    0.46
     ____
    0.46
     ----
    0.46
     "--
    0.44
    )--
    0.44
    "--
    0.44
     ---
    0.43
    Activations Density 0.796%

    No Known Activations