© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8731
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to projects, plans, and academic research

    oai_token-act-pair · gemini-2.0-flash

    Describing plans and features

    np_max-act-logits · gemini-2.0-flash

    say "include" Method used: 2 — because following tokens are predominantly "include"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     henvisninger
    -0.50
     muualla
    -0.50
     play
    -0.49
     Play
    -0.48
    play
    -0.46
    Havolalar
    -0.46
     fool
    -0.46
    includes
    -0.45
    туга
    -0.45
     lead
    -0.45
    POSITIVE LOGITS
     feature
    1.23
     Feature
    1.05
    feature
    1.03
     FEATURE
    0.90
    Feature
    0.88
    FEATURE
    0.73
    出版年
    0.70
    AndEndTag
    0.69
    principalTable
    0.63
     BoxDecoration
    0.60
    Activations Density 5.573%

    No Known Activations