© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8123
    Prev
    Next
    INDEX
    Explanations

    single letters, especially those followed by punctuation, numbers with some relevance to citations in scientific publications, URL components, and some names

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
    nosaurus
    -0.44
     alimentaires
    -0.41
    burns
    -0.40
    mallows
    -0.40
    hampton
    -0.40
    otides
    -0.40
    IUrlHelper
    -0.39
    washer
    -0.38
    addCriterion
    -0.38
    rowave
    -0.38
    POSITIVE LOGITS
    enapa
    0.65
    enseits
    0.56
    ientôt
    0.55
    ագրություններ
    0.55
    iritto
    0.54
    essoas
    0.54
    ovács
    0.53
    warzys
    0.50
    rvats
    0.50
     gddr
    0.50
    Activations Density 8.536%

    No Known Activations