© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9807
    Prev
    Next
    INDEX
    Explanations

    mentions of things turning out well or badly

    oai_token-act-pair · gemini-2.0-flash

    turned/turn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    phrag
    -0.48
    sproz
    -0.44
    zko
    -0.42
    runApp
    -0.41
    BURGH
    -0.41
    尼斯
    -0.40
    postDelayed
    -0.40
    macher
    -0.40
    anese
    -0.40
    ⓧ
    -0.39
    POSITIVE LOGITS
     turned
    2.44
     turn
    2.41
     turning
    2.30
     Turn
    2.23
    turn
    2.20
     Turned
    2.19
    Turn
    2.17
     turns
    2.14
     TURN
    2.13
    turned
    2.11
    Activations Density 2.835%

    No Known Activations