© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11463
    Prev
    Next
    INDEX
    Explanations

    the string "sch" followed by other letters

    oai_token-act-pair · gemini-2.0-flash

    sch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Sch
    -2.41
    Sch
    -2.28
     sch
    -2.20
    sch
    -2.06
    SCH
    -1.58
     SCH
    -1.52
    <bos>
    -1.10
    ssch
    -1.05
     Sche
    -0.94
    esch
    -0.89
    POSITIVE LOGITS
    StoryboardSegue
    0.67
    InjectAttribute
    0.63
     betweenstory
    0.62
     ProductService
    0.59
    Eller
    0.59
    PhysRev
    0.58
     FontWeight
    0.58
     caverns
    0.56
    resave
    0.56
     choker
    0.55
    Activations Density 0.322%

    No Known Activations