© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2076
    Prev
    Next
    INDEX
    Explanations

    phrases or words that contain prefixes or suffixes, especially those related to opposition or time

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    
    -0.65
    __':
    -0.61
    __':
    -0.61
    '}),
    -0.60
     `.
    -0.57
    SharedCtor
    -0.56
    "]));
    -0.55
    ')){
    -0.55
    brainly
    -0.54
    ▻
    -0.54
    POSITIVE LOGITS
     refusé
    0.57
     betrek
    0.56
     normaux
    0.55
     découver
    0.55
     iconFacebook
    0.54
    slavery
    0.54
     spéciaux
    0.54
     noires
    0.53
     negras
    0.53
     complètes
    0.52
    Activations Density 8.863%

    No Known Activations