© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    uppercase words related to standards, specifications, or official documentation

    oai_token-act-pair · gemini-2.0-flash

    Code and formal text

    np_max-act-logits · gemini-2.0-flash

    say "suffixes" Method used: 2 — because the tokens after complete prefixes into full word endings; say "suffixes"

    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
    l
    -0.91
    r
    -0.63
    lte
    -0.60
    lng
    -0.58
    lle
    -0.56
    lde
    -0.55
    lara
    -0.52
    lty
    -0.52
    lr
    -0.50
    E
    -0.50
    POSITIVE LOGITS
    L
    0.75
    ModelAdmin
    0.61
     تضيفلها
    0.57
    Lm
    0.48
    RRect
    0.48
     Chwiliwch
    0.47
    NSYLVANIA
    0.47
    এ
    0.47
    __':
    0.47
    RIO
    0.46
    Activations Density 7.809%

    No Known Activations