© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5627
    Prev
    Next
    INDEX
    Explanations

    terminology related to statistical estimation and machine learning

    oai_token-act-pair · gemini-2.0-flash

    specific statistical terms or variables

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

    statistical estimators discussion

    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
     Roskov
    -0.75
     typelib
    -0.73
     Мексичка
    -0.59
     Brecht
    -0.58
    derung
    -0.58
    Personensuche
    -0.57
    Isolated
    -0.57
    stateMutability
    -0.56
    EndGlobalSection
    -0.56
    Geplaatst
    -0.56
    POSITIVE LOGITS
    SequentialGroup
    0.60
     R
    0.54
    asaan
    0.50
     imp
    0.49
    R
    0.47
    ESSOR
    0.46
    ParameterName
    0.46
     Rubin
    0.44
    styleable
    0.44
     Gel
    0.44
    Activations Density 14.267%

    No Known Activations