© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6830
    Prev
    Next
    INDEX
    Explanations

    the word "signed."

    oai_token-act-pair · gemini-2.0-flash

    signed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     devenus
    -0.80
     déchir
    -0.80
     démission
    -0.79
     accél
    -0.79
     genitori
    -0.76
     recev
    -0.76
     détru
    -0.74
     représ
    -0.74
     déclen
    -0.73
     refroid
    -0.73
    POSITIVE LOGITS
    <bos>
    0.63
     rule
    0.62
    انيف
    0.61
    RTN
    0.59
     SEP
    0.56
    ribute
    0.56
    ^(@)
    0.56
    Transcripción
    0.56
    BoxShadow
    0.56
    Xiaomi
    0.55
    Activations Density 1.612%

    No Known Activations