© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 509
    Prev
    Next
    INDEX
    Explanations

    mentions in a narrative of past violence and death

    oai_token-act-pair · gemini-2.0-flash

    learn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    帖最后由
    -0.60
    acic
    -0.51
     بيها
    -0.50
     Signalez
    -0.49
    InstanceState
    -0.48
    StoryboardSegue
    -0.47
    igshid
    -0.45
    WaitGroup
    -0.44
     архивлан
    -0.44
    tvguidetime
    -0.44
    POSITIVE LOGITS
    $.
    0.66
    });*/
    0.65
     kaarangay
    0.62
     itſelf
    0.61
    المناصب
    0.61
    fillType
    0.61
    )");
    0.61
    NonQuery
    0.60
     Baillargeon
    0.59
    niosek
    0.59
    Activations Density 24.724%

    No Known Activations