© 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. 6787
    Prev
    Next
    INDEX
    Explanations

    words related to fantasy stories, with words like journey, tales, and book

    oai_token-act-pair · gemini-2.0-flash

    names of places

    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
    GEBURTSDATUM
    -0.66
     transfieras
    -0.60
    principalTable
    -0.54
     Offisielt
    -0.52
    ValueStyle
    -0.50
    Portail
    -0.50
     دیکھیے
    -0.50
     بتاريخ
    -0.49
    Personendaten
    -0.49
     virš
    -0.48
    POSITIVE LOGITS
     Pa
    0.77
     Lu
    0.75
     Te
    0.74
     Ke
    0.73
     Mi
    0.73
     Bu
    0.72
     Ba
    0.72
     Wa
    0.71
     Ru
    0.71
     Ma
    0.71
    Activations Density 16.561%

    No Known Activations