© 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. 4420
    Prev
    Next
    INDEX
    Explanations

    the word "pack" and a couple of other seemingly random words

    oai_token-act-pair · gemini-2.0-flash

    pack

    np_max-act · gemini-2.0-flash

    ▁pack

    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
     overall
    -0.57
     udaler
    -0.56
    SerializedName
    -0.55
     hand
    -0.54
    øya
    -0.52
    WriteAttribute
    -0.51
    utable
    -0.51
     error
    -0.51
     engagement
    -0.50
     mind
    -0.50
    POSITIVE LOGITS
     ?'
    0.90
    évaluateur
    0.86
     ''}
    0.84
     industriels
    0.77
     :—
    0.75
    '>";
    0.74
    .’”
    0.74
    —"
    0.73
     ?”
    0.73
     ?"
    0.73
    Activations Density 1.776%

    No Known Activations