© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15551
    Prev
    Next
    INDEX
    Explanations

    code that contains patterns of single character operators like '/' or '.' surrounded by other characters

    oai_token-act-pair · gemini-2.0-flash

    unorthodox identifiers or variable names

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

    Javascript properties/methods

    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
    Negative Logits
    .
    -0.83
    .,
    -0.49
    ,
    -0.48
    .-
    -0.45
    —
    -0.42
    !
    -0.42
     @
    -0.41
    ’
    -0.40
     on
    -0.40
     at
    -0.39
    POSITIVE LOGITS
    MemoryWarning
    1.01
    #+#
    1.01
    +#+
    1.00
     myſelf
    0.92
     pleaſure
    0.90
     Monfieur
    0.85
    Obrázky
    0.84
     Majefty
    0.82
    ſelf
    0.82
     purpoſe
    0.81
    Activations Density 0.537%

    No Known Activations