© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10775
    Prev
    Next
    INDEX
    Explanations

    sentences in the third person that discuss other people

    oai_token-act-pair · gemini-2.0-flash

    follow

    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
    ########.
    -0.52
     ExecuteAsync
    -0.51
    ⟭
    -0.50
    yente
    -0.47
     Book
    -0.47
    ashian
    -0.47
    ラク
    -0.44
     onBind
    -0.44
    base
    -0.43
    Book
    -0.43
    POSITIVE LOGITS
     follow
    0.94
    follow
    0.81
    Follow
    0.80
     Follow
    0.77
    FOLLOW
    0.76
    脚注の使い方
    0.71
     follows
    0.71
     FOLLOW
    0.69
     كومونز
    0.69
     followup
    0.68
    Activations Density 3.856%

    No Known Activations