© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5604
    Prev
    Next
    INDEX
    Explanations

    references to US politics and international relations.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

    np_token-act-pair-logits · gpt-4o-mini

    international politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Климат
    -0.48
    <?>>
    -0.47
    haden
    -0.46
     cocco
    -0.46
    ucha
    -0.46
    ()];
    -0.46
    yout
    -0.45
    "?>
    -0.44
    ]->
    -0.44
    licone
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.80
    findpost
    0.78
    verifyException
    0.67
    RTLR
    0.66
    хьтан
    0.64
    Personendaten
    0.60
    évaluateur
    0.60
    fjspx
    0.59
     Савезне
    0.58
    SharedDtor
    0.56
    Activations Density 8.650%

    No Known Activations