© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12100
    Prev
    Next
    INDEX
    Explanations

    the words "climb" and/or "cave"

    oai_token-act-pair · gemini-2.0-flash

    identifiers or keywords related to programming

    np_token-act-pair-logits · gpt-4o-mini

    climb

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     myſelf
    -0.92
    BufferException
    -0.84
     Monfieur
    -0.84
    parsedMessage
    -0.84
     faſt
    -0.79
     leaſt
    -0.79
    (!__
    -0.78
     publick
    -0.76
     becauſe
    -0.75
     كومونز
    -0.73
    POSITIVE LOGITS
    IDI
    0.51
    Mode
    0.50
     route
    0.48
     e
    0.47
     Mode
    0.47
     log
    0.46
     mode
    0.45
     down
    0.45
     J
    0.45
     Mar
    0.44
    Activations Density 1.115%

    No Known Activations