© 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. 6676
    Prev
    Next
    INDEX
    Explanations

    code syntax, especially C/C++ related code

    oai_token-act-pair · gemini-2.0-flash

    t

    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
    ագրություններ
    -0.60
     []:
    -0.60
     consultato
    -0.58
    ing
    -0.54
    ($__
    -0.52
    例句
    -0.52
    havi
    -0.51
     Instrum
    -0.49
     noten
    -0.48
    ber
    -0.48
    POSITIVE LOGITS
    <bos>
    1.59
     Monfieur
    1.01
     Efq
    0.98
     itſelf
    0.98
     myſelf
    0.94
     chofe
    0.86
     Shakspeare
    0.84
     himſelf
    0.83
     Theſe
    0.81
     Cæsar
    0.80
    Activations Density 2.723%

    No Known Activations