© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7499
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of" preceded by a word indicating amount or number

    oai_token-act-pair · gemini-2.0-flash

    Influential topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     as
    -0.66
     beyond
    -0.59
     and
    -0.56
     within
    -0.52
     in
    -0.52
     leading
    -0.50
     on
    -0.48
     inside
    -0.46
     or
    -0.45
     across
    -0.44
    POSITIVE LOGITS
     Shakspeare
    1.08
     Jefus
    1.08
     houſe
    1.06
     pleaſure
    1.05
     purpoſe
    1.04
     Monfieur
    1.03
     Efq
    1.03
     juſt
    1.02
     raiſ
    1.00
     ſhe
    0.98
    Activations Density 5.345%

    No Known Activations