© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13356
    Prev
    Next
    INDEX
    Explanations

    the word "stamp" along with words associated with dates and small amounts

    oai_token-act-pair · gemini-2.0-flash

    stamp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .
    -0.98
    ,
    -0.97
     $
    -0.92
     por
    -0.87
     (
    -0.86
     \
    -0.86
     dan
    -0.85
     es
    -0.82
     et
    -0.82
     _
    -0.82
    POSITIVE LOGITS
     itſelf
    2.50
     myſelf
    2.38
     Efq
    2.28
     Monfieur
    2.16
     Theſe
    2.14
     Anſ
    2.06
     Houſe
    2.05
     Reſ
    2.02
     Jefus
    2.00
    ſelves
    1.99
    Activations Density 2.989%

    No Known Activations