© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11335
    Prev
    Next
    INDEX
    Explanations

    descriptions of how circuits or machines work

    oai_token-act-pair · gemini-2.0-flash

    signal processing, circuits

    np_max-act · gemini-2.0-flash

    verbs ending in s

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     DPM
    -0.79
    xFFFFFFFF
    -0.72
    CloseOperation
    -0.69
    UserScript
    -0.66
    uesia
    -0.66
    numerusform
    -0.65
     ESM
    -0.64
    TargetException
    -0.63
     Siles
    -0.63
     IES
    -0.63
    POSITIVE LOGITS
    <bos>
    1.37
     the
    0.71
    '
    0.68
    ’
    0.68
    IUrlHelper
    0.65
     a
    0.60
    TagMode
    0.59
     it
    0.58
     
    0.55
    the
    0.55
    Activations Density 1.000%

    No Known Activations