© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3440
    Prev
    Next
    INDEX
    Explanations

    instances of the syllable "Ho", "Go", "So", "Co" and "Ko"

    oai_token-act-pair · gemini-2.0-flash

    Ho

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ly
    -0.69
    men
    -0.64
    her
    -0.62
    ya
    -0.62
    by
    -0.60
    ko
    -0.59
    ku
    -0.59
    yo
    -0.59
    fully
    -0.58
    w
    -0.58
    POSITIVE LOGITS
     CURIAM
    0.47
     cru
    0.47
    ckeys
    0.45
    strze
    0.45
    XmlAccessorType
    0.44
     CanadaChoose
    0.44
    enumi
    0.43
    发表于
    0.43
    addGap
    0.42
    клопе
    0.42
    Activations Density 0.399%

    No Known Activations