© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10696
    Prev
    Next
    INDEX
    Explanations

    C++ or Objective-C code

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     المعيارى
    -0.88
    TemporalType
    -0.85
    rungsseite
    -0.81
     متعلقه
    -0.75
     auffi
    -0.73
     Efq
    -0.71
    TintMode
    -0.70
    ſhip
    -0.68
    CppMethod
    -0.66
     auroit
    -0.66
    POSITIVE LOGITS
    ul
    0.54
    off
    0.47
    ma
    0.45
    da
    0.43
    ue
    0.43
    ik
    0.43
    gar
    0.42
    g
    0.42
    rak
    0.41
    gra
    0.41
    Activations Density 0.172%

    No Known Activations