© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9659
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rather", and "more...than"

    oai_token-act-pair · gemini-2.0-flash

    comparisons and contrasts

    np_token-act-pair-logits · gpt-4o-mini

    than

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    تے
    -0.56
     Signalez
    -0.52
    tels
    -0.49
    ところです
    -0.49
    riguez
    -0.48
    laterra
    -0.47
    PrototypeOf
    -0.47
    evich
    -0.47
    不对
    -0.46
    avax
    -0.46
    POSITIVE LOGITS
     than
    3.39
     THAN
    2.39
    than
    2.20
    Than
    2.09
     Than
    2.05
     niż
    1.76
     än
    1.73
    THAN
    1.72
     kuin
    1.61
     než
    1.60
    Activations Density 1.375%

    No Known Activations