© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10366
    Prev
    Next
    INDEX
    Explanations

    jewelry and possibly other indicators of wealth

    oai_token-act-pair · gemini-2.0-flash

    Time/watches

    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
    rungsseite
    -0.85
    tagHelperRunner
    -0.81
    TypedDataSet
    -0.75
    Rüyada
    -0.71
    verwijspagina
    -0.63
     nahilalakip
    -0.59
     defaultstate
    -0.58
    COUVER
    -0.57
    WidgetItem
    -0.57
     CanadaChoose
    -0.56
    POSITIVE LOGITS
    PreExecute
    0.50
    mphony
    0.49
     Christo
    0.48
     oyster
    0.46
    ousand
    0.46
    BITDA
    0.46
    oa̍t
    0.45
     SIMBAD
    0.45
     Hetero
    0.44
    BoxShadow
    0.43
    Activations Density 0.708%

    No Known Activations