© 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. 3478
    Prev
    Next
    INDEX
    Explanations

    the word "three" and numbers/words that describe a quantity

    oai_token-act-pair · gemini-2.0-flash

    three

    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
     two
    -2.14
     three
    -1.82
     four
    -1.55
     five
    -1.37
     first
    -1.16
     the
    -1.16
     six
    -1.16
     seven
    -1.09
     deux
    -1.08
     eight
    -1.06
    POSITIVE LOGITS
     masts
    0.96
    +#+#
    0.87
     <<<<<<<<<<<<<<
    0.84
    GEBURTSDATUM
    0.81
     Outro
    0.80
     EEU
    0.80
    addPreferredGap
    0.80
     Fascism
    0.78
     Negroes
    0.78
     pyjamas
    0.77
    Activations Density 2.085%

    No Known Activations