© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4766
    Prev
    Next
    INDEX
    Explanations

    clauses that use lots of pronouns and conjunctions in a short span.

    oai_token-act-pair · gemini-2.0-flash

    lie

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ruptedException
    -0.75
    锈钢
    -0.67
    SPATH
    -0.64
    رشف
    -0.61
    OGND
    -0.59
    Rhestr
    -0.57
    verwijspagina
    -0.57
     CreateTagHelper
    -0.56
    Дереккөздер
    -0.56
    UserScript
    -0.56
    POSITIVE LOGITS
     lie
    1.90
     lies
    1.66
     lying
    1.49
    Lie
    1.42
     Lie
    1.37
     lay
    1.31
     Lying
    1.28
    Lying
    1.27
     LIE
    1.27
     Lies
    1.21
    Activations Density 4.119%

    No Known Activations