© 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. 3935
    Prev
    Next
    INDEX
    Explanations

    clauses expressing personal opinions and experiences

    oai_token-act-pair · gemini-2.0-flash

    unexpected punctuation and expressions

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

    Bad events

    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
    ChildScrollView
    -0.82
    WriteTagHelper
    -0.63
    》.
    -0.58
     >::
    -0.57
     ModelExpression
    -0.56
    xnn
    -0.52
    '):
    -0.51
     connais
    -0.51
     préfère
    -0.51
    ">.
    -0.51
    POSITIVE LOGITS
    !
    0.65
    Coordonnées
    0.56
     stuff
    0.56
    ThroughAttribute
    0.54
    !—
    0.52
    !--
    0.50
     ooo
    0.50
    oooo
    0.49
     apl
    0.49
     STUFF
    0.49
    Activations Density 2.687%

    No Known Activations