© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16237
    Prev
    Next
    INDEX
    Explanations

    instances of comparison, possibly indicating an analysis or study

    oai_token-act-pair · gemini-2.0-flash

    compared

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     محفوظة
    -0.67
     समीक्षक
    -0.60
    AndEndTag
    -0.59
     propOrder
    -0.59
    বহ
    -0.59
     MainAxisSize
    -0.58
     découvertes
    -0.58
     feux
    -0.58
     cérami
    -0.57
     récompenses
    -0.57
    POSITIVE LOGITS
    tagHelperRunner
    0.59
     w
    0.53
    CppMethod
    0.49
    RefNanny
    0.47
    IDTH
    0.47
     W
    0.47
    orothy
    0.46
    SharedCtor
    0.46
    Einen
    0.45
    ToolStrip
    0.45
    Activations Density 20.030%

    No Known Activations