© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13645
    Prev
    Next
    INDEX
    Explanations

    references to a group of people or many people

    oai_token-act-pair · gemini-2.0-flash

    many

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ReusableCell
    -0.84
    TintMode
    -0.84
    setViewportView
    -0.81
     raiſ
    -0.78
     itſelf
    -0.76
     becauſe
    -0.70
     dreamstime
    -0.69
     ſche
    -0.69
     defStyle
    -0.69
     doubtnut
    -0.69
    POSITIVE LOGITS
     who
    0.88
     have
    0.83
     are
    0.78
     were
    0.77
     see
    0.76
     find
    0.71
     visit
    0.69
     say
    0.68
     look
    0.68
     consider
    0.66
    Activations Density 8.456%

    No Known Activations