© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4174
    Prev
    Next
    INDEX
    Explanations

    language of positive and negative description

    oai_token-act-pair · 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
     resourceCulture
    -0.57
    LikeLike
    -0.48
    AnchorStyles
    -0.46
     مشارکت‌کنندگان
    -0.43
    RectangleBorder
    -0.43
    providedIn
    -0.42
     TOC
    -0.42
     Hra
    -0.42
     Shaker
    -0.41
    na
    -0.41
    POSITIVE LOGITS
    uxxxx
    0.84
     Roskov
    0.77
    ViewFeatures
    0.69
    uação
    0.69
    OGND
    0.68
    Distribuzione
    0.66
    hyrchwyd
    0.64
     Италијани
    0.64
     OMITBAD
    0.63
     kasarigan
    0.62
    Activations Density 4.172%

    No Known Activations