© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8300
    Prev
    Next
    INDEX
    Explanations

    hexadecimal codes

    oai_token-act-pair · gemini-2.0-flash

    encoding or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     x
    -0.62
     i
    -0.58
     ist
    -0.55
    RESUMO
    -0.53
     l
    -0.53
     y
    -0.52
     il
    -0.52
    Παραπομπές
    -0.52
     u
    -0.51
     z
    -0.51
    POSITIVE LOGITS
    ſelf
    0.94
    ſelves
    0.85
     Monfieur
    0.81
     Anſ
    0.81
     myſelf
    0.77
     ſtate
    0.76
     itſelf
    0.76
     pleaſure
    0.76
     ſeveral
    0.75
     houſe
    0.75
    Activations Density 16.546%

    No Known Activations