© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hold" or its derivatives.

    oai_token-act-pair · gemini-2.0-flash

    fast

    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
     Roskov
    -0.59
     "..\..\
    -0.58
     hold
    -0.56
     "..\..\..\
    -0.54
    hold
    -0.51
     समीक्षाएं
    -0.49
     فريبيس
    -0.46
     Wikispecies
    -0.46
    RTEX
    -0.46
     nahilalakip
    -0.46
    POSITIVE LOGITS
     fast
    2.39
    fast
    2.17
    Fast
    2.09
     Fast
    2.05
     FAST
    1.63
    FAST
    1.60
     faſt
    1.28
     faster
    1.09
     fastest
    1.05
     rápido
    0.99
    Activations Density 6.016%

    No Known Activations