© 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. 13114
    Prev
    Next
    INDEX
    Explanations

    parts of code that deal with image icons, delimiters, size, and installation directories

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    <bos>
    -0.51
    ’
    -0.45
    >>
    -0.40
     dia
    -0.39
    dir
    -0.39
    '
    -0.37
    dia
    -0.36
    Pa
    -0.35
     indisponible
    -0.35
    mi
    -0.35
    POSITIVE LOGITS
    CloseOperation
    0.96
     Мексичка
    0.84
     myſelf
    0.82
     propOrder
    0.82
    ACIONAL
    0.80
    ]--;
    0.79
    amaño
    0.78
     poffible
    0.76
    теризу
    0.75
     Monfieur
    0.75
    Activations Density 2.992%

    No Known Activations