© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6714
    Prev
    Next
    INDEX
    Explanations

    the possessive form of nouns

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    DockStyle
    -1.23
    <bos>
    -1.03
    SequentialGroup
    -0.98
     itſelf
    -0.93
     myſelf
    -0.91
     doubtnut
    -0.88
     ExecuteAsync
    -0.85
     Anſ
    -0.82
     ་་
    -0.81
    ^(@)
    -0.81
    POSITIVE LOGITS
     his
    1.17
     His
    0.78
     
    0.76
     her
    0.75
     "
    0.74
    彼の
    0.73
     Her
    0.72
     original
    0.71
     (
    0.69
     sua
    0.69
    Activations Density 0.317%

    No Known Activations