© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5930
    Prev
    Next
    INDEX
    Explanations

    the word "chance" and pronouns

    oai_token-act-pair · gemini-2.0-flash

    chance

    np_max-act · gemini-2.0-flash

    ▁chance

    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
    UnsafeEnabled
    -1.00
    ValueStyle
    -0.81
     purpoſe
    -0.79
     ſtate
    -0.76
     myſelf
    -0.75
     étoient
    -0.72
    berdayakan
    -0.71
    warnai
    -0.70
     gebeurt
    -0.70
     Theſe
    -0.69
    POSITIVE LOGITS
    SuppressLint
    0.76
    ↵↵
    0.69
     ‘
    0.68
    ########.
    0.68
    ())));
    0.68
     “
    0.64
    ’
    0.58
    stdio
    0.56
     pulumi
    0.56
    AnimationFrame
    0.56
    Activations Density 0.944%

    No Known Activations