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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12994
    Prev
    Next
    INDEX
    Explanations

    geographical coordinates and nautical measurements

    oai_token-act-pair · gemini-2.0-flash

    Math and science

    np_max-act-logits · gemini-2.0-flash
    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
    inser
    -0.46
    lapsible
    -0.44
    Inser
    -0.44
    ssing
    -0.43
     leaking
    -0.42
     pulled
    -0.42
     Pulled
    -0.42
     Pacheco
    -0.42
    osing
    -0.42
    afety
    -0.42
    POSITIVE LOGITS
     TestBed
    0.76
    rungsseite
    0.73
     arşivlendi
    0.56
    soort
    0.54
    出版年
    0.54
    saraba
    0.54
    iastes
    0.54
    findpost
    0.54
    verwijspagina
    0.53
    Zulu
    0.53
    Activations Density 27.482%

    No Known Activations