© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15690
    Prev
    Next
    INDEX
    Explanations

    a mix of sentence structure, official documentation, and personal pronouncements

    oai_token-act-pair · gemini-2.0-flash

    legal/official documentation

    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
    goto
    -0.74
    Came
    -0.69
     went
    -0.69
     perish
    -0.68
     stays
    -0.68
     rises
    -0.66
     died
    -0.66
     morire
    -0.66
     Goes
    -0.66
     stay
    -0.66
    POSITIVE LOGITS
    oneofs
    0.63
    modb
    0.57
    tvguidetime
    0.56
     Numerade
    0.56
     Lightboxes
    0.55
    gebob
    0.54
    PhysRevD
    0.51
    ükemmel
    0.50
    بوابة
    0.50
    rungsseite
    0.50
    Activations Density 2.177%

    No Known Activations