© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10604
    Prev
    Next
    INDEX
    Explanations

    the number 199 followed by another single digit

    oai_token-act-pair · gemini-2.0-flash

    9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    adaptiveStyles
    -0.97
     '\\;'
    -0.88
     NSCoder
    -0.84
    WriteBarrier
    -0.79
     kaynağından
    -0.79
    ImageContext
    -0.77
    sizeCache
    -0.75
     &___
    -0.71
    AccessorTable
    -0.70
     مرئيه
    -0.69
    POSITIVE LOGITS
    meck
    0.42
    9
    0.40
    C
    0.40
     riuscito
    0.40
    #{
    0.40
    0
    0.40
    8
    0.39
     Glou
    0.39
    cus
    0.39
    #+#
    0.38
    Activations Density 0.673%

    No Known Activations