© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7401
    Prev
    Next
    INDEX
    Explanations

    technical texts about angles, especially in relation to light or machine parts

    oai_token-act-pair · gemini-2.0-flash

    angles and rotations

    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
     Angle
    -1.91
     angle
    -1.85
     angles
    -1.81
     Angles
    -1.76
     Ang
    -1.76
     ANGLE
    -1.74
     ANG
    -1.73
    Angle
    -1.69
    Ang
    -1.63
    angle
    -1.61
    POSITIVE LOGITS
    webElementXpaths
    0.55
     disponibilités
    0.52
     للمعارف
    0.51
     okuyayım
    0.48
    TestTools
    0.47
     McCormack
    0.47
     disambiguazione
    0.46
     betweenstory
    0.45
    কার
    0.44
    atsby
    0.43
    Activations Density 2.035%

    No Known Activations