© 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. 15469
    Prev
    Next
    INDEX
    Explanations

    content that looks like programming code and/or comments in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
     del
    -1.15
     el
    -1.00
     du
    -0.87
     Del
    -0.85
     het
    -0.82
     DEL
    -0.81
     Mr
    -0.76
    el
    -0.75
    del
    -0.75
     il
    -0.74
    POSITIVE LOGITS
     nakalista
    0.69
    enumii
    0.68
    cazione
    0.68
    enterOuterAlt
    0.67
     חיצוניים
    0.60
    La
    0.59
    IsContent
    0.58
     >=",
    0.58
     يتيمه
    0.58
     la
    0.57
    Activations Density 1.916%

    No Known Activations