© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11365
    Prev
    Next
    INDEX
    Explanations

    mentions of characters embarking on a new or difficult life journey

    oai_token-act-pair · gemini-2.0-flash

    words related to paths and downward movement

    np_token-act-pair-logits · gpt-4o-mini

    journeys and paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IVEREF
    -0.74
     surla
    -0.72
     cherchés
    -0.72
    DrawerToggle
    -0.70
    quelize
    -0.66
    PreferredItem
    -0.63
     ddelweddau
    -0.62
    مصادر
    -0.62
    Rhestr
    -0.60
    )++;
    -0.60
    POSITIVE LOGITS
     down
    0.84
     path
    0.74
     Down
    0.71
    Down
    0.71
    Path
    0.68
     paths
    0.68
    path
    0.66
     along
    0.61
    down
    0.60
     DOWN
    0.60
    Activations Density 1.715%

    No Known Activations