© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14128
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, especially those found in C++ or Java

    oai_token-act-pair · gemini-2.0-flash

    unusual or non-standard text patterns

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

    coding 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
     N
    -0.81
     Z
    -0.65
     K
    -0.63
     A
    -0.60
     L
    -0.60
     H
    -0.60
     B
    -0.60
     W
    -0.59
     J
    -0.58
     n
    -0.57
    POSITIVE LOGITS
     doubtnut
    0.93
     preſent
    0.91
    Vidite
    0.90
    oredCriteria
    0.88
     فريبيس
    0.84
     Anſ
    0.84
     Reſ
    0.84
     itſelf
    0.83
     Diſ
    0.82
     ་་
    0.82
    Activations Density 7.103%

    No Known Activations