© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14147
    Prev
    Next
    INDEX
    Explanations

    strings of non-alphanumeric characters and math formulas

    oai_token-act-pair · gemini-2.0-flash

    code and latex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Theſe
    -1.45
     Monfieur
    -1.25
     avoient
    -1.21
     myſelf
    -1.21
     étoit
    -1.20
     Efq
    -1.20
     étoient
    -1.17
     auroit
    -1.16
     Houſe
    -1.14
     feroit
    -1.13
    POSITIVE LOGITS
    </strong>
    0.79
     to
    0.79
    </em>
    0.78
     |
    0.77
     in
    0.76
    -
    0.75
     $
    0.71
     ‘
    0.71
     [
    0.71
    "
    0.71
    Activations Density 2.115%

    No Known Activations