© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12009
    Prev
    Next
    INDEX
    Explanations

    phrases that are prepositions combined with nouns

    oai_token-act-pair · gemini-2.0-flash

    personal stories

    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
     their
    -0.80
     his
    -0.71
     ihre
    -0.67
     ihren
    -0.63
     sua
    -0.62
     her
    -0.61
     ihr
    -0.60
     ihres
    -0.59
     ihrer
    -0.59
     your
    -0.58
    POSITIVE LOGITS
    المكان
    0.65
     يتيمه
    0.60
    لیس
    0.59
     theſe
    0.55
     initComponents
    0.54
     Tripura
    0.53
    SourceChecksum
    0.53
    
    0.52
    انگلیسی
    0.52
     Haarlem
    0.52
    Activations Density 11.024%

    No Known Activations