© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14555
    Prev
    Next
    INDEX
    Explanations

    the word "but" and words that act like "but".

    oai_token-act-pair · gemini-2.0-flash

    But/However

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    +#+#
    -0.57
     externi
    -0.57
    Same
    -0.56
     nakalista
    -0.55
     gleicher
    -0.53
     Same
    -0.52
     hetzelfde
    -0.52
    Personendaten
    -0.52
     насеље
    -0.52
     derselben
    -0.51
    POSITIVE LOGITS
     surla
    0.72
     different
    0.60
     distinct
    0.59
     tartalomajánló
    0.55
    +#+
    0.55
    Distinct
    0.53
     specific
    0.53
    different
    0.52
     distinctly
    0.52
    ressum
    0.50
    Activations Density 0.288%

    No Known Activations