© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical documentation, possibly related to configuration files, URLs, and string manipulation

    oai_token-act-pair · gemini-2.0-flash

    say quotation marks

    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
     “
    -0.92
     ‘
    -0.89
     الرياضيه
    -0.78
     «
    -0.75
     ‘’
    -0.65
    Portale
    -0.63
     continúas
    -0.61
    =”
    -0.60
    udadera
    -0.60
    expandindo
    -0.59
    POSITIVE LOGITS
    "
    2.25
    '
    2.11
    ''
    1.53
    ”
    1.41
    ’
    1.38
    `
    1.32
    "'
    1.28
    '"
    1.27
    “
    1.26
    ‘
    1.23
    Activations Density 9.730%

    No Known Activations