© 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. 309
    Prev
    Next
    INDEX
    Explanations

    a variety of different kinds of structural markup, including numbers, code, and internet forum posts.

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign text

    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
    CodedInputStream
    -0.35
     Efq
    -0.33
    neſs
    -0.33
     $_"
    -0.32
    ]--;
    -0.32
     fermés
    -0.31
    ſelf
    -0.30
     Jefus
    -0.29
     ContentValues
    -0.28
     automatiques
    -0.28
    POSITIVE LOGITS
     ISNI
    0.53
    ViewImports
    0.48
     Chwiliwch
    0.43
    appé
    0.42
    chafft
    0.42
     papy
    0.42
     Rimini
    0.41
     Esperanto
    0.41
     referenties
    0.41
    Хьажоргаш
    0.41
    Activations Density 6.425%

    No Known Activations