© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3382
    Prev
    Next
    INDEX
    Explanations

    the word "long" and words of similar context, combined with medical or scientific terminology.

    oai_token-act-pair · gemini-2.0-flash

    long

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     LONG
    -1.12
     long
    -1.12
     Long
    -1.04
    tagHelperRunner
    -1.04
     Longer
    -1.03
    LONG
    -1.02
     panjang
    -1.02
     longer
    -1.01
     longs
    -0.98
    long
    -0.97
    POSITIVE LOGITS
    other
    0.44
    gend
    0.43
     rosado
    0.41
    i
    0.40
    Other
    0.40
    vi
    0.40
    <eos>
    0.38
     Privacidade
    0.38
    diali
    0.38
    Map
    0.38
    Activations Density 29.862%

    No Known Activations