© 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. 12593
    Prev
    Next
    INDEX
    Explanations

    proper nouns including locations and organizations, often followed by numbers or percentages

    oai_token-act-pair · gemini-2.0-flash

    news and events

    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
    ########.
    -0.58
     bezeichneter
    -0.56
     Efq
    -0.54
    UnusedPrivate
    -0.51
     Theſe
    -0.50
     Monfieur
    -0.47
     Jefus
    -0.47
     Anſ
    -0.46
    parsedMessage
    -0.45
     Italijanski
    -0.45
    POSITIVE LOGITS
    IMAN
    0.65
     Manor
    0.64
    aurus
    0.63
     is
    0.61
     Monkeys
    0.60
    )))),
    0.60
     Whales
    0.60
    siri
    0.60
     Mania
    0.59
     Donuts
    0.59
    Activations Density 4.793%

    No Known Activations