© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3294
    Prev
    Next
    INDEX
    Explanations

    language that attempts to motivate or influence the reader

    oai_token-act-pair · gemini-2.0-flash

    self-help advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IntoConstraints
    -0.65
    principalTable
    -0.63
    enterOuterAlt
    -0.63
    MessageTagHelper
    -0.60
     beginnetje
    -0.56
    দ্ধ
    -0.56
    pfung
    -0.52
    ennifer
    -0.50
    adaptiveStyles
    -0.50
     Roskov
    -0.49
    POSITIVE LOGITS
     live
    0.57
     ?>/
    0.54
     تضيفلها
    0.51
    <?
    0.51
    FilterChain
    0.49
     redis
    0.49
     према
    0.48
    saurus
    0.47
     Стре
    0.47
    anskje
    0.46
    Activations Density 0.846%

    No Known Activations