© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5132
    Prev
    Next
    INDEX
    Explanations

    instances of capitalized name fragments followed closely by a 1-2 character fragment

    oai_token-act-pair · gemini-2.0-flash

    eld

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ,
    -0.60
    …
    -0.49
    ↵↵
    -0.49
     (
    -0.49
     i
    -0.48
    :
    -0.46
     B
    -0.44
     I
    -0.44
     and
    -0.44
    .
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    1.54
     Мексичка
    1.50
    ContentAsync
    1.41
    Personensuche
    1.40
    +#+#
    1.38
     تضيفلها
    1.30
     незавершена
    1.29
    abestanden
    1.27
    uxxxx
    1.27
     فريبيس
    1.23
    Activations Density 1.535%

    No Known Activations