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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5469
    Prev
    Next
    INDEX
    Explanations

    places where the author is making a point or transitioning between topics

    oai_token-act-pair · gemini-2.0-flash

    sentences with "turn" or its variations

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

    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_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
     ModelExpression
    -0.70
    Autoritní
    -0.61
     kaynağından
    -0.57
    Források
    -0.57
    Aiheesta
    -0.57
    Diweddarwch
    -0.57
    Scénario
    -0.55
     autorytatywna
    -0.55
    вгений
    -0.55
    OGND
    -0.54
    POSITIVE LOGITS
     turns
    0.80
     turn
    0.76
    turns
    0.68
    ThroughAttribute
    0.68
     turned
    0.63
     Turns
    0.61
     TURN
    0.59
    Turns
    0.58
     Turn
    0.57
    turn
    0.57
    Activations Density 1.881%

    No Known Activations