© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4310
    Prev
    Next
    INDEX
    Explanations

    a mix of portuguese and croatian words, often verbs, in a programming context.

    oai_token-act-pair · gemini-2.0-flash

    non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.09
     
    -0.68
     the
    -0.58
     to
    -0.53
     in
    -0.53
     more
    -0.51
    rotnie
    -0.50
    ↵↵
    -0.49
     by
    -0.49
     con
    -0.48
    POSITIVE LOGITS
     Majefty
    0.90
     purpoſe
    0.88
     feroit
    0.87
     myſelf
    0.87
     iſt
    0.85
     Diſ
    0.85
     occaf
    0.85
     pleaſure
    0.84
     cauſe
    0.83
     MainAxisSize
    0.83
    Activations Density 0.262%

    No Known Activations