© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3044
    Prev
    Next
    INDEX
    Explanations

    the word "it" or phrases containing the word "it"

    oai_token-act-pair · gemini-2.0-flash

    it

    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
     FontWeight
    -0.72
    ]")]
    -0.69
    modb
    -0.65
    ソッド
    -0.65
     StatefulWidget
    -0.63
    expandindo
    -0.62
    примеча
    -0.61
    BASEPATH
    -0.61
     protoimpl
    -0.60
    NameInMap
    -0.60
    POSITIVE LOGITS
     arrives
    0.65
     comes
    0.64
     gets
    0.63
     arises
    0.60
     occurs
    0.60
     feels
    0.57
     seems
    0.57
     goes
    0.55
     belongs
    0.55
     begins
    0.54
    Activations Density 4.269%

    No Known Activations