© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    text written in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    Mixed language support/help forum

    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
     propOrder
    -0.71
     تعدى
    -0.65
    __':
    -0.63
     per
    -0.59
    +#+#
    -0.59
    ReusableCell
    -0.58
    ッケージ
    -0.57
     odkazy
    -0.56
    enoord
    -0.56
     ujednoznacz
    -0.54
    POSITIVE LOGITS
    mybatisplus
    0.62
    MigrationBuilder
    0.54
    NegativeButton
    0.53
    openzeppelin
    0.53
    yandex
    0.51
    ⓒ
    0.50
    Configurer
    0.50
    aktur
    0.50
    TintMode
    0.48
    ',)
    0.47
    Activations Density 0.871%

    No Known Activations