© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12734
    Prev
    Next
    INDEX
    Explanations

    technical terms

    oai_token-act-pair · gemini-2.0-flash

    Generic academic research

    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
     Theſe
    -0.77
    AndEndTag
    -0.76
     EconPapers
    -0.74
     Majefty
    -0.72
     Reſ
    -0.71
    脚注の使い方
    -0.70
     resourceCulture
    -0.70
     itſelf
    -0.68
     <<<<<<<<<<<<<<
    -0.68
     ویکی‌پدی
    -0.67
    POSITIVE LOGITS
     is
    1.07
     be
    0.76
     was
    0.71
     —
    0.57
     will
    0.57
     can
    0.56
     remains
    0.54
     being
    0.53
     are
    0.53
    —
    0.50
    Activations Density 17.336%

    No Known Activations