© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11592
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives like easier and stronger, sometimes in the context of arguments or comparisons being made.

    oai_token-act-pair · gemini-2.0-flash

    comparative adjectives

    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
    Not in Any Lists

    No Comments

    Negative Logits
    easier
    -1.34
     easier
    -1.34
     safer
    -1.33
     purer
    -1.31
     funnier
    -1.30
     Easier
    -1.27
     smoother
    -1.26
    Easier
    -1.26
     bolder
    -1.25
     louder
    -1.24
    POSITIVE LOGITS
    Наводи
    0.54
    Bissau
    0.52
     position
    0.50
    ivores
    0.50
    rungsseite
    0.49
     high
    0.49
     and
    0.48
     clear
    0.48
    bastien
    0.48
     hight
    0.48
    Activations Density 2.471%

    No Known Activations