© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8463
    Prev
    Next
    INDEX
    Explanations

    words in formal writing, especially legal, academic and technological writing, about rules, cases, keys, groups, and teams

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    vų
    -0.45
    binaan
    -0.44
    haltens
    -0.44
    weichen
    -0.44
    ofman
    -0.42
    können
    -0.42
    plaatst
    -0.41
    iomanip
    -0.41
    zwungen
    -0.41
    themselves
    -0.40
    POSITIVE LOGITS
    board
    1.06
    point
    1.05
    work
    1.03
    books
    1.02
    points
    1.02
    ground
    1.02
    boat
    1.01
    room
    1.00
    light
    0.99
    book
    0.99
    Activations Density 34.860%

    No Known Activations