© 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. 3852
    Prev
    Next
    INDEX
    Explanations

    words that appear to be important or technical terms

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     �
    -0.98
     â
    -0.97
     Â
    -0.85
     &#
    -0.82
     صوتيه
    -0.82
     Ã
    -0.81
     ``
    -0.77
     ‘‘
    -0.76
     ​
    -0.75
     lenker
    -0.73
    POSITIVE LOGITS
    ”
    1.52
    "
    1.41
    ?
    1.22
    」
    1.22
    "?
    1.11
    ”?
    1.10
    ”.
    1.09
    ",
    1.08
    ".
    1.07
    ”,
    1.06
    Activations Density 5.533%

    No Known Activations