© 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. 4241
    Prev
    Next
    INDEX
    Explanations

    "which" relative clauses, often preceded by "that"

    oai_token-act-pair · gemini-2.0-flash

    which

    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
    }`;
    -0.63
    abestanden
    -0.62
    >`;
    -0.60
    ført
    -0.55
    醐
    -0.55
    testens
    -0.53
     scolaires
    -0.51
     porcentual
    -0.50
     mẽ
    -0.50
    >";
    -0.50
    POSITIVE LOGITS
     ones
    0.65
    تقاوى
    0.63
    erent
    0.58
     Nib
    0.58
    MenuGroup
    0.57
    blade
    0.57
    soever
    0.56
    yim
    0.55
    unsch
    0.55
     hee
    0.54
    Activations Density 1.246%

    No Known Activations