© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14748
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to function definitions, conditional statements, or JSON handling

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     itſelf
    -1.11
     fubject
    -1.10
     myſelf
    -1.05
     whoſe
    -1.03
     ſtate
    -1.00
     raiſ
    -0.98
     purpoſe
    -0.95
    <bos>
    -0.94
     pleaſure
    -0.93
     themſelves
    -0.92
    POSITIVE LOGITS
     or
    0.45
     net
    0.44
    htë
    0.44
    .
    0.43
    <sup>
    0.42
     vor
    0.42
    <sub>
    0.42
     “
    0.40
     so
    0.40
     de
    0.38
    Activations Density 20.477%

    No Known Activations