© 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. 4115
    Prev
    Next
    INDEX
    Explanations

    extended ascii characters.

    oai_token-act-pair · gemini-2.0-flash

    Mixed 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
     mellitus
    -0.26
    __);
    -0.26
     Continent
    -0.22
     continent
    -0.22
     Athenian
    -0.21
     immemorial
    -0.20
     torchvision
    -0.20
    BeginContext
    -0.20
     AssemblyCompany
    -0.20
     Confucius
    -0.19
    POSITIVE LOGITS
     démocr
    0.63
    Geplaatst
    0.63
     fédé
    0.61
     mauvaises
    0.61
     riuscito
    0.59
    migrationBuilder
    0.58
     juridiques
    0.57
     publiques
    0.57
     ongles
    0.56
    håll
    0.56
    Activations Density 4.526%

    No Known Activations