© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14925
    Prev
    Next
    INDEX
    Explanations

    sentences discussing what one does or does not deserve

    oai_token-act-pair · gemini-2.0-flash

    deserve

    np_max-act · gemini-2.0-flash

    deserve

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <u>
    -0.65
    2
    -0.56
    1
    -0.54
    <h3>
    -0.54
     most
    -0.53
    I
    -0.51
    正
    -0.51
    こと
    -0.51
    er
    -0.50
    re
    -0.50
    POSITIVE LOGITS
     betweenstory
    1.03
    StoryboardSegue
    0.95
     resourceCulture
    0.89
     متعلقه
    0.88
    LookAnd
    0.88
     onOptions
    0.84
    innocent
    0.82
    Londres
    0.76
     '\\;'
    0.76
     createState
    0.75
    Activations Density 0.967%

    No Known Activations