© 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. 8462
    Prev
    Next
    INDEX
    Explanations

    phrases including the words "reason", "some", or "for"

    oai_token-act-pair · gemini-2.0-flash

    Qualifying a previous statement

    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
     why
    -3.08
    why
    -2.67
     reasons
    -2.59
     Why
    -2.47
    Why
    -2.38
    reasons
    -2.38
     Reasons
    -2.30
     WHY
    -2.19
    WHY
    -2.19
     pourquoi
    -2.19
    POSITIVE LOGITS
     estimés
    0.51
    Hauptartikel
    0.49
    вена
    0.39
     saites
    0.39
    ("."
    0.39
    scriptId
    0.38
    :+:
    0.37
    Handled
    0.37
     vors
    0.37
     $=$
    0.36
    Activations Density 2.746%

    No Known Activations