© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9977
    Prev
    Next
    INDEX
    Explanations

    system error codes

    oai_token-act-pair · gemini-2.0-flash

    say "e" words

    np_max-act-logits · gemini-2.0-flash

    say "e" Method used: 2 — because following tokens begin with "e"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    u
    -0.67
    o
    -0.62
    uth
    -0.57
    uating
    -0.56
    odes
    -0.56
    op
    -0.56
    opro
    -0.55
    og
    -0.55
    od
    -0.54
    odic
    -0.54
    POSITIVE LOGITS
    e
    0.90
    es
    0.89
    eb
    0.83
    ed
    0.76
    er
    0.74
    eh
    0.71
    et
    0.71
    е
    0.70
    emen
    0.68
    ec
    0.68
    Activations Density 14.632%

    No Known Activations