© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7877
    Prev
    Next
    INDEX
    Explanations

    words related to thought and shared characteristics.

    oai_token-act-pair · gemini-2.0-flash

    common thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     utilising
    -0.60
     recognises
    -0.60
    centred
    -0.60
     whilst
    -0.60
     centre
    -0.59
    ysing
    -0.59
     centred
    -0.58
     localised
    -0.58
    usermodel
    -0.58
     Favourite
    -0.57
    POSITIVE LOGITS
    SharedDtor
    0.65
    UnknownFields
    0.65
    SourceChecksum
    0.63
    ConstraintMaker
    0.62
     jScrollPane
    0.60
     ModelExpression
    0.59
    GOTREF
    0.59
     Chwiliwch
    0.58
     initComponents
    0.54
     testified
    0.52
    Activations Density 1.715%

    No Known Activations