© 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. 23
    Prev
    Next
    INDEX
    Explanations

    mentions of knowledge, values, traditions or skills being passed on between people, often between generations

    oai_token-act-pair · gemini-2.0-flash

    say "on"

    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
     passing
    -3.33
     pass
    -3.14
     Passing
    -3.06
    Passing
    -3.05
    passing
    -2.94
     Pass
    -2.91
    pass
    -2.89
    Pass
    -2.84
     passes
    -2.83
     passed
    -2.78
    POSITIVE LOGITS
     محفوظة
    0.73
     utafitiHapana
    0.46
    isInitialized
    0.45
    덱
    0.45
    gdx
    0.44
     Niños
    0.44
    GroupLayout
    0.43
    ั้ง
    0.43
    breng
    0.43
     actionPerformed
    0.43
    Activations Density 2.282%

    No Known Activations