© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4331
    Prev
    Next
    INDEX
    Explanations

    code snippets and tags related to ListBox, Panel, and DataGridView in C# or Javascript

    oai_token-act-pair · gemini-2.0-flash

    Coding elements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ConstraintMaker
    -0.82
     setuptools
    -0.66
     betweenstory
    -0.64
    MessageState
    -0.63
    IVEREF
    -0.60
    RTLD
    -0.59
    queryInterface
    -0.57
     TextInputType
    -0.55
    mybatisplus
    -0.55
    FieldBuilder
    -0.54
    POSITIVE LOGITS
     насељу
    0.68
    ]=>
    0.53
    Clik
    0.51
     juridiques
    0.51
    hockey
    0.48
     Mindest
    0.45
     Hon
    0.45
     hiệp
    0.45
    lera
    0.44
     golongan
    0.43
    Activations Density 4.281%

    No Known Activations