© 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. 4056
    Prev
    Next
    INDEX
    Explanations

    code snippets or mathematical equations, especially those involving coordinates or trigonometry

    oai_token-act-pair · gemini-2.0-flash

    rotation and angles

    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
     ویکی‌پدیا
    -0.60
     Affiliations
    -0.53
    جوايز
    -0.51
     Abstracts
    -0.51
    PubMed
    -0.51
     Suppliers
    -0.50
     FetchType
    -0.50
     Wikispecies
    -0.50
    +#+#
    -0.50
     Disqus
    -0.49
    POSITIVE LOGITS
    Rotated
    0.57
    angle
    0.56
     Rot
    0.54
    Rotation
    0.54
    Rot
    0.54
     Contour
    0.53
    Angle
    0.52
    Rotate
    0.51
     ANGLE
    0.50
    Curve
    0.50
    Activations Density 26.241%

    No Known Activations