© 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. 7975
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" or numbers, especially in the context of events, exhibitions, or scientific topics

    oai_token-act-pair · gemini-2.0-flash

    sign

    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
     fi
    -1.53
     fl
    -1.41
     first
    -1.37
    fi
    -1.21
    fl
    -1.14
    matchCondition
    -1.13
     
    -1.02
    :✨
    -0.99
    IsContent
    -0.98
    parsedMessage
    -0.98
    POSITIVE LOGITS
     sign
    1.43
     Sign
    1.07
     di
    0.94
    Sign
    0.94
    sign
    0.91
     SIGN
    0.80
    SIGN
    0.75
    sig
    0.74
     con
    0.73
     signos
    0.68
    Activations Density 1.059%

    No Known Activations