© 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. 1482
    Prev
    Next
    INDEX
    Explanations

    references to legal cases, guilt or innocence, arguments, intent, and decisions within the justice system.

    oai_token-act-pair · gemini-2.0-flash

    morality and judgement

    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
    IUrlHelper
    -1.02
    OGND
    -0.96
    AddTagHelper
    -0.94
     &___
    -0.93
    IntoConstraints
    -0.91
    Personendaten
    -0.86
     فريبيس
    -0.84
    MigrationBuilder
    -0.82
    AccessorTable
    -0.77
     resourceCulture
    -0.77
    POSITIVE LOGITS
    "]/
    0.44
    Html
    0.44
     sp
    0.42
    Phas
    0.42
     Html
    0.42
     vẻ
    0.41
     html
    0.41
     deleteUser
    0.40
    lines
    0.39
    ibos
    0.39
    Activations Density 6.172%

    No Known Activations