© 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. 6740
    Prev
    Next
    INDEX
    Explanations

    legal or scientific documents with cited cases, footnotes, and dates

    oai_token-act-pair · gemini-2.0-flash

    legal/academic documents

    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
    Below
    -0.81
     Below
    -0.77
     BELOW
    -0.63
    below
    -0.61
     below
    -0.56
    Above
    -0.49
    下面
    -0.46
     Beyond
    -0.41
     ниже
    -0.40
    Beyond
    -0.40
    POSITIVE LOGITS
    CloseOperation
    0.84
    Portail
    0.71
    LLocation
    0.71
    principalColumn
    0.71
    WebVitals
    0.68
    FailureListener
    0.66
     IActionResult
    0.65
    المشاركات
    0.64
     plagioclase
    0.63
    醐
    0.63
    Activations Density 26.528%

    No Known Activations