© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3343
    Prev
    Next
    INDEX
    Explanations

    code snippets using the keyword "get"

    oai_token-act-pair · gemini-2.0-flash

    the 'Get' function and related keywords

    np_token-act-pair-logits · gpt-4o-mini

    Get

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     obtain
    -0.62
     to
    -0.59
     obtained
    -0.59
     Obtain
    -0.58
     obtaining
    -0.55
     получить
    -0.53
     obtenir
    -0.52
    Obtain
    -0.52
    vå
    -0.51
     Obtained
    -0.50
    POSITIVE LOGITS
    出版年
    0.90
    WriteTagHelper
    0.63
    featureID
    0.62
    GOTREF
    0.60
    aktery
    0.59
    saraba
    0.58
     посту
    0.58
    oredCriteria
    0.58
    glTexCoord
    0.57
    ScopeManager
    0.56
    Activations Density 1.309%

    No Known Activations