© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4506
    Prev
    Next
    INDEX
    Explanations

    words ending in "ide" or words related to luck and links

    oai_token-act-pair · gemini-2.0-flash

    ide

    np_max-act · gemini-2.0-flash

    say "space" Method used: 2 — tokens mostly start with a leading space, so say "space"

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.54
     يتيمه
    -1.41
     itſelf
    -1.39
     Efq
    -1.33
     ་་
    -1.31
     ſind
    -1.30
    ^(@)
    -1.29
     himſelf
    -1.29
     whoſe
    -1.27
     doubtnut
    -1.25
    POSITIVE LOGITS
    ly
    0.71
     "
    0.69
    <eos>
    0.63
    ten
    0.61
     du
    0.60
    .
    0.59
     (
    0.58
     =
    0.57
    ↵↵
    0.56
    a
    0.55
    Activations Density 1.536%

    No Known Activations