© 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. 13685
    Prev
    Next
    INDEX
    Explanations

    text that discusses family history and genealogy

    oai_token-act-pair · gemini-2.0-flash

    Positive memories and nostalgia

    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
     Anſ
    -0.75
    UnknownFields
    -0.74
    AndEndTag
    -0.72
    HasAnnotation
    -0.69
     يتيمه
    -0.69
     ErrIntOverflow
    -0.69
    ſelf
    -0.67
     AssemblyCulture
    -0.66
    Diweddarwch
    -0.63
     Conſ
    -0.60
    POSITIVE LOGITS
     times
    0.66
    times
    0.57
     time
    0.51
    Lähteet
    0.49
     gạch
    0.49
    jubljana
    0.47
     TIMES
    0.45
     special
    0.44
     som
    0.43
     okuyayım
    0.43
    Activations Density 5.922%

    No Known Activations