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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14765
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers followed by quantities of homes and buildings in the context of destruction.

    oai_token-act-pair · gemini-2.0-flash

    not English words

    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
     house
    -2.34
    house
    -1.94
    House
    -1.84
     House
    -1.82
     HOUSE
    -1.80
    HOUSE
    -1.73
     home
    -1.69
    home
    -1.47
     casa
    -1.46
     huis
    -1.45
    POSITIVE LOGITS
    الإنجليزية
    0.56
    MarshalTo
    0.54
    Tembelea
    0.49
    getWriter
    0.48
    setopt
    0.47
    Vezi
    0.47
    addPreferredGap
    0.46
    _+
    0.46
    Rptr
    0.46
    oredCriteria
    0.45
    Activations Density 2.882%

    No Known Activations