© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14904
    Prev
    Next
    INDEX
    Explanations

    comparative phrases using "not only", "but also", and "both"

    oai_token-act-pair · gemini-2.0-flash

    limitations and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    IndentedString
    -0.85
    Portale
    -0.79
     للاسماء
    -0.75
    principalColumn
    -0.75
     فريبيس
    -0.73
     Monfieur
    -0.70
     fevere
    -0.66
    IsContent
    -0.66
    :");
    -0.64
     Signalez
    -0.64
    POSITIVE LOGITS
     unless
    0.59
     partly
    0.57
     Unless
    0.54
     moins
    0.54
    Билгалдахарш
    0.52
    veys
    0.51
     because
    0.51
     bien
    0.50
    agne
    0.50
     allem
    0.49
    Activations Density 3.877%

    No Known Activations