© 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. 3250
    Prev
    Next
    INDEX
    Explanations

    the string "Rec"

    oai_token-act-pair · gemini-2.0-flash

    'Rec' prefix or variations

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

    Rec

    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
    脚注の使い方
    -0.76
    httphttps
    -0.61
     createState
    -0.60
    ServletConfig
    -0.57
    醐
    -0.55
    SpringBootTest
    -0.55
    drawSprites
    -0.54
     initComponents
    -0.52
    ArgsConstructor
    -0.52
    CreateModel
    -0.51
    POSITIVE LOGITS
    ITATION
    0.54
     nakalista
    0.48
    contentLoaded
    0.47
    onso
    0.47
    uteur
    0.46
     Ny
    0.46
    tant
    0.45
     équilibr
    0.45
     Lu
    0.45
     Vikipedi
    0.45
    Activations Density 0.577%

    No Known Activations