© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5854
    Prev
    Next
    INDEX
    Explanations

    words frequently used in song or television show titles, especially if following "The", and musical jargon.

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    ContentAlignment
    -0.67
    Tell
    -0.59
     Commencez
    -0.57
    It
    -0.57
    lück
    -0.56
    ering
    -0.55
     It
    -0.54
    клопе
    -0.54
    writerow
    -0.54
    ElementException
    -0.53
    POSITIVE LOGITS
     nakalista
    0.47
    RectangleBorder
    0.47
     Realms
    0.46
    الإنجليزية
    0.44
    Belgique
    0.43
     Stairs
    0.43
     Waterways
    0.42
     séjours
    0.40
     multiverse
    0.40
     Stacks
    0.39
    Activations Density 9.622%

    No Known Activations