© 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. 12679
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes and strings of letters and numbers

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    i
    -1.20
    y
    -0.85
    ScopeManager
    -0.76
     CreateTagHelper
    -0.75
    e
    -0.74
    ił
    -0.72
    usermodel
    -0.71
    ی
    -0.67
    parsedMessage
    -0.67
     arşivlendi
    -0.67
    POSITIVE LOGITS
    ez
    0.51
    ev
    0.49
    oz
    0.48
    ais
    0.44
    ama
    0.44
    an
    0.43
     isComment
    0.42
     AssemblyTitle
    0.41
    aa
    0.40
    oon
    0.38
    Activations Density 2.665%

    No Known Activations