© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10069
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to reasons, purposes, and motivations

    oai_token-act-pair · gemini-2.0-flash

    Reasons/rationale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     виправивши
    -0.96
     الحره
    -0.78
     Biôgrafia
    -0.69
     linkovi
    -0.68
    expandindo
    -0.65
    actionMode
    -0.65
    JNIEnv
    -0.64
    PreferredItem
    -0.62
     beginnetje
    -0.60
    }}],
    -0.59
    POSITIVE LOGITS
     reason
    0.86
     reasons
    0.86
     Reasons
    0.84
     why
    0.83
    why
    0.82
    Reasons
    0.80
    Why
    0.75
    reasons
    0.75
     Waarom
    0.74
     REASONS
    0.73
    Activations Density 1.469%

    No Known Activations