© 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. 2883
    Prev
    Next
    INDEX
    Explanations

    percent encoded characters

    oai_token-act-pair · gemini-2.0-flash

    percentage values or statistics

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

    2

    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
    PreferredItem
    -0.63
    Rüyada
    -0.60
    SpringBootTest
    -0.59
    featureID
    -0.59
    WriteLiteral
    -0.58
    下载附件
    -0.54
    InstrumentedTest
    -0.52
    DeleteBehavior
    -0.51
    AddTagHelper
    -0.51
    hasMoreElements
    -0.50
    POSITIVE LOGITS
    Personendaten
    0.66
    odle
    0.53
    complexContent
    0.47
    CSP
    0.46
    ViewChild
    0.46
     MSD
    0.45
    stdc
    0.45
     Ato
    0.44
     onOptions
    0.44
     stessi
    0.44
    Activations Density 1.032%

    No Known Activations