© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14561
    Prev
    Next
    INDEX
    Explanations

    words related to family, health and outdoor activities

    oai_token-act-pair · gemini-2.0-flash

    Events and activities

    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
    Kjelder
    -0.51
    zzleHttp
    -0.45
    (&:
    -0.44
    伐
    -0.44
    Agre
    -0.43
    TAGE
    -0.43
    kler
    -0.43
    ⓘ
    -0.42
     تانيه
    -0.42
     GME
    -0.42
    POSITIVE LOGITS
     ModelExpression
    1.01
    
    0.67
    enschappe
    0.66
    AddTagHelper
    0.66
     تضيفلها
    0.66
     pinulongan
    0.66
    AccessorTable
    0.64
    RectangleBorder
    0.61
    ندية
    0.60
     виправивши
    0.60
    Activations Density 6.173%

    No Known Activations