© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6612
    Prev
    Next
    INDEX
    Explanations

    the word "except" and words used in exclusions

    oai_token-act-pair · gemini-2.0-flash

    except

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -2.27
     except
    -1.90
    except
    -1.73
    Except
    -1.69
     Except
    -1.64
     sauf
    -1.48
     kecuali
    -1.41
     excepto
    -1.39
     EXCEPT
    -1.33
    EXCEPT
    -1.20
    POSITIVE LOGITS
     Deeds
    0.59
    ViewInit
    0.57
    ürtel
    0.57
     Milling
    0.56
    AutoScaleMode
    0.56
     GoogleFonts
    0.55
     Mousse
    0.55
    逅
    0.52
     Domes
    0.50
     Agre
    0.50
    Activations Density 0.356%

    No Known Activations