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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2016
    Prev
    Next
    INDEX
    Explanations

    tokens indicating something spatially

    oai_token-act-pair · gemini-2.0-flash

    Locations and placements

    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
     front
    -2.84
    front
    -2.50
    Front
    -2.48
     Front
    -2.45
     FRONT
    -2.31
    FRONT
    -2.20
     fronts
    -1.88
     frontend
    -1.51
    fron
    -1.49
     frente
    -1.48
    POSITIVE LOGITS
     समीक्षाओं
    0.63
    Бахар
    0.63
    SPATH
    0.62
     betweenstory
    0.60
    脚注の使い方
    0.59
     ExecuteAsync
    0.59
     CreateTagHelper
    0.56
    ⓘ
    0.53
     esboço
    0.52
    تقاوى
    0.52
    Activations Density 4.451%

    No Known Activations