© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6829
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly random characters and formatting

    oai_token-act-pair · gemini-2.0-flash

    Non-English text and code

    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
    SequentialGroup
    -0.93
    ConstraintMaker
    -0.92
     يتيمه
    -0.76
    LLocation
    -0.73
     wireType
    -0.73
    awtextra
    -0.73
    Personensuche
    -0.72
    tagHelper
    -0.72
     للمعارف
    -0.71
    PYX
    -0.71
    POSITIVE LOGITS
    ็ง
    0.63
    ราะ
    0.59
    ือก
    0.52
    ี้ย
    0.51
    ียว
    0.51
     surla
    0.49
    ๋า
    0.49
    ี่ยว
    0.45
    าะ
    0.43
    ื้น
    0.42
    Activations Density 0.218%

    No Known Activations