© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6955
    Prev
    Next
    INDEX
    Explanations

    the first person pronouns, the word "to", words related to discussion and sharing, and the phrase "be careful not to include spoilers"

    oai_token-act-pair · gemini-2.0-flash

    spoilers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    glLoadIdentity
    -0.64
     الدولى
    -0.64
    انيف
    -0.60
     fhew
    -0.58
     Majefty
    -0.56
    EndTag
    -0.56
    Tikang
    -0.55
     himo
    -0.54
    <?,
    -0.54
     gagne
    -0.53
    POSITIVE LOGITS
     spoilers
    1.02
     spoiler
    1.00
     SPOILER
    0.90
     Spoiler
    0.87
     SPOILERS
    0.79
     Spoilers
    0.78
    spoiler
    0.77
    Spoiler
    0.75
    spo
    0.69
     spoil
    0.65
    Activations Density 0.466%

    No Known Activations