© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2706
    Prev
    Next
    INDEX
    Explanations

    varied, but tends to target sections of text making an argument or describing a scene with people.

    oai_token-act-pair · gemini-2.0-flash

    Society/media/culture

    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
     galima
    -0.59
     oreilles
    -0.53
    Šaltiniai
    -0.50
     nationaux
    -0.46
     découvertes
    -0.46
     natten
    -0.45
     Италијани
    -0.45
     numéros
    -0.43
     connues
    -0.43
     varmt
    -0.42
    POSITIVE LOGITS
     apply
    1.05
     consume
    0.98
     look
    0.96
     testify
    0.93
     emerge
    0.92
     undergo
    0.91
     come
    0.91
     relate
    0.90
     weigh
    0.89
     evolve
    0.89
    Activations Density 8.597%

    No Known Activations