© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12091
    Prev
    Next
    INDEX
    Explanations

    personal pronouns immediately preceded by the word 'where', and words ending in 'ia', 'ri', 'on', 'uk', 'athan, 'ishi' AND the word 'enable'

    oai_token-act-pair · gemini-2.0-flash

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    awtextra
    -0.83
    Brainz
    -0.63
    ConstraintMaker
    -0.63
    abestanden
    -0.56
     beginnetje
    -0.55
    曖昧さ回避
    -0.55
    CPtr
    -0.54
     Lokales
    -0.52
    Rüyada
    -0.51
     imprend
    -0.49
    POSITIVE LOGITS
     nakalista
    0.57
    fecture
    0.51
     kick
    0.50
    substack
    0.49
    kick
    0.49
     NgModule
    0.49
    yelitis
    0.48
    jonen
    0.48
    ereum
    0.48
    brainly
    0.47
    Activations Density 0.633%

    No Known Activations