© 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. 8688
    Prev
    Next
    INDEX
    Explanations

    instances of "it" followed by a form of an auxiliary verb and/or certain modal verbs

    oai_token-act-pair · gemini-2.0-flash

    t

    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
    ThroughAttribute
    -0.98
    ReusableCell
    -0.78
    parsedMessage
    -0.77
    findpost
    -0.72
     <<<<<<<<<<<<<<
    -0.72
    InputLabel
    -0.71
     resourceCulture
    -0.70
    istoitu
    -0.69
    (;;)
    -0.68
    Hauptartikel
    -0.67
    POSITIVE LOGITS
     She
    0.46
     shaken
    0.37
    She
    0.37
    l
    0.36
    }}
    0.35
    ova
    0.35
     mať
    0.35
     fuga
    0.34
     shake
    0.34
    NotEqualTo
    0.33
    Activations Density 2.306%

    No Known Activations