© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13559
    Prev
    Next
    INDEX
    Explanations

    the prefix "sub"

    oai_token-act-pair · gemini-2.0-flash

    instances of "sub"

    np_token-act-pair-logits · gpt-4o-mini

    sub

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DoubleQuotes
    -0.66
    ніципа
    -0.55
     bouch
    -0.52
    brero
    -0.48
    原始内容存档于
    -0.47
    :\/\/
    -0.47
    ictwa
    -0.45
    ATIVES
    -0.44
     dram
    -0.44
     CanadaChoose
    -0.43
    POSITIVE LOGITS
    行政区划
    0.59
     Corpo
    0.54
    tagHelperRunner
    0.51
    RUnlock
    0.51
    providedIn
    0.51
    ParallelGroup
    0.51
    ruptedException
    0.50
     Prose
    0.50
     насељу
    0.49
    IGraphics
    0.48
    Activations Density 0.809%

    No Known Activations