© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10687
    Prev
    Next
    INDEX
    Explanations

    the "ra" syllable

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "ra"

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

    ra

    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
    φη
    -0.49
     onOptions
    -0.47
    archiviato
    -0.47
    apimachinery
    -0.46
     idén
    -0.44
    OptionsMenu
    -0.44
    ORIA
    -0.44
    ValueGeneration
    -0.44
    amazonaws
    -0.43
     rác
    -0.43
    POSITIVE LOGITS
    UnknownFields
    0.60
    })`
    0.56
    脚注の使い方
    0.54
    Życiorys
    0.54
    ujudkan
    0.53
     saites
    0.52
    endphp
    0.52
     صوتيه
    0.51
    Kjelder
    0.50
    こんにちは
    0.50
    Activations Density 0.224%

    No Known Activations