© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8357
    Prev
    Next
    INDEX
    Explanations

    the word "arm"

    oai_token-act-pair · gemini-2.0-flash

    arm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -0.77
     final
    -0.74
    <eos>
    -0.74
     die
    -0.70
     der
    -0.68
     v
    -0.63
     un
    -0.63
     of
    -0.63
     original
    -0.63
     na
    -0.62
    POSITIVE LOGITS
     myſelf
    1.48
     purpoſe
    1.44
    ########.
    1.42
     Majefty
    1.33
     houſe
    1.32
     itſelf
    1.32
     Efq
    1.28
    ſelf
    1.25
     Houſe
    1.23
     ainfi
    1.23
    Activations Density 2.127%

    No Known Activations