© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11317
    Prev
    Next
    INDEX
    Explanations

    words about loss, ceasing to exist, or being removed.

    oai_token-act-pair · gemini-2.0-flash

    words related to experiences of absence or loss

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

    vanish, disappear

    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
     disambiguazione
    -0.63
    "])
    
    -0.63
    setupUi
    -0.62
    ]=>
    -0.61
    SharedCtor
    -0.60
     ModelExpression
    -0.56
    ChildScrollView
    -0.55
    GEBURTSDATUM
    -0.55
    ">:
    -0.55
    omeness
    -0.54
    POSITIVE LOGITS
     popoli
    0.52
     giustizia
    0.52
     handcuffs
    0.49
     coloré
    0.49
    Super
    0.48
     lettore
    0.48
     Euphrates
    0.47
     doccia
    0.47
    mení
    0.47
    IVEREF
    0.46
    Activations Density 7.249%

    No Known Activations