© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11189
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that could be part of an argument in favor of a particular position

    oai_token-act-pair · gemini-2.0-flash

    say punctuation after token

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -2.56
     myſelf
    -2.22
     Theſe
    -2.22
     itſelf
    -2.13
     Monfieur
    -2.09
     purpoſe
    -2.05
     Majefty
    -2.03
     houſe
    -2.03
     himſelf
    -2.00
     Jefus
    -2.00
    POSITIVE LOGITS
    <eos>
    0.53
    &
    0.46
    ’
    0.44
     
    0.44
      
    0.40
    1
    0.40
    '
    0.40
    &#
    0.39
    \
    0.39
    <unused63>
    0.38
    Activations Density 23.607%

    No Known Activations