Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9699
    Prev
    Next
    INDEX
    Explanations

    words related to data collection, scientific reports, and studies.

    oai_token-act-pair · gemini-2.0-flash

    organization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     '{@
    -0.64
    RenderAtEndOf
    -0.63
    MigrationBuilder
    -0.60
     arranged
    -0.59
     organised
    -0.56
    HideFlags
    -0.53
     organized
    -0.53
    kulum
    -0.52
     Arranged
    -0.51
     coordinated
    -0.49
    POSITIVE LOGITS
     organization
    2.50
     organisation
    2.38
     Organization
    2.08
     Organisation
    1.98
    organization
    1.95
    Organization
    1.92
     ORGANIZATION
    1.91
    organisation
    1.77
     organisatie
    1.75
     organización
    1.72
    Activations Density 7.922%

    No Known Activations