© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13243
    Prev
    Next
    INDEX
    Explanations

    words that indicate a progress or change of state

    oai_token-act-pair · gemini-2.0-flash

    technical keywords or terms

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

    Code/technical language

    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
     removed
    -0.77
     dismissed
    -0.76
     selected
    -0.73
     picked
    -0.70
     arrested
    -0.69
     awarded
    -0.69
     replaced
    -0.69
     rescued
    -0.69
     killed
    -0.67
     granted
    -0.66
    POSITIVE LOGITS
     unknownFields
    0.63
    ImageContext
    0.60
     '\\;'
    0.60
    AutoScaleMode
    0.58
     invokingState
    0.57
     ProtoMessage
    0.56
     purpoſe
    0.54
     internetowa
    0.54
    ModelSerializer
    0.52
    Cyfarwyddwr
    0.52
    Activations Density 2.941%

    No Known Activations