© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3321
    Prev
    Next
    INDEX
    Explanations

    the letter S, even when surrounded by other letters, numbers, or punctuation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     lenker
    -0.60
    üyada
    -0.58
    下载附件
    -0.54
    UNRELATED
    -0.50
     invol
    -0.46
    obel
    -0.46
    readAs
    -0.45
     pro
    -0.45
     basic
    -0.44
    basic
    -0.43
    POSITIVE LOGITS
     réguli
    0.59
    DockStyle
    0.59
    uxxxx
    0.59
     découver
    0.58
     useRouter
    0.57
    <bos>
    0.54
    NUMX
    0.53
     financières
    0.52
     Trench
    0.52
     quelque
    0.52
    Activations Density 1.115%

    No Known Activations