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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3800
    Prev
    Next
    INDEX
    Explanations

    code snippets, configuration files or code-related documentation

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     Monfieur
    -0.70
     Eſ
    -0.70
     myſelf
    -0.69
     vertes
    -0.68
    daß
    -0.66
    '},
    -0.66
     iſt
    -0.65
     Jefus
    -0.65
     يتيمه
    -0.65
     Wikiseite
    -0.65
    POSITIVE LOGITS
    S
    0.33
    for
    0.33
     AFS
    0.31
    “
    0.30
    _
    0.29
    C
    0.29
    v
    0.29
    *
    0.28
     MEA
    0.28
    on
    0.27
    Activations Density 15.811%

    No Known Activations