© 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. 13405
    Prev
    Next
    INDEX
    Explanations

    lines of code containing periods/full stops that are part of object accessors and mutators in a program that utilizes buttons and panels

    oai_token-act-pair · gemini-2.0-flash

    punctuations and formatting symbols

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

    punctuation

    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
    Espèce
    -0.54
     crossorigin
    -0.49
    nodoc
    -0.49
     افتراض
    -0.49
    Extinguishing
    -0.48
     bourgeo
    -0.46
    rshire
    -0.46
    refour
    -0.46
    liosis
    -0.46
     gł
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.71
    jaan
    0.61
    +:+
    0.60
    BackStack
    0.55
    PYX
    0.55
     estimés
    0.54
    AutoresizingMask
    0.53
    [['
    0.53
    pozdrawiam
    0.52
    Pozdrawiam
    0.52
    Activations Density 0.312%

    No Known Activations