© 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. 786
    Prev
    Next
    INDEX
    Explanations

    a mixture of math symbols, equation fragments, and hyphenated words

    oai_token-act-pair · gemini-2.0-flash

    "u"

    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
    es
    -0.88
    e
    -0.85
    eb
    -0.76
    ed
    -0.73
    ES
    -0.70
    er
    -0.70
    et
    -0.66
    е
    -0.65
    eh
    -0.64
    eba
    -0.64
    POSITIVE LOGITS
    u
    0.73
    uth
    0.67
    o
    0.63
    og
    0.60
    och
    0.59
    op
    0.58
    opro
    0.58
    oo
    0.58
    uating
    0.57
    uy
    0.57
    Activations Density 17.106%

    No Known Activations