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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9975
    Prev
    Next
    INDEX
    Explanations

    the verb "to be" in various tenses

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code-related keywords

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

    was

    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
    tamanya
    -0.47
    #
    -0.47
    obacterium
    -0.43
    atrician
    -0.41
     umane
    -0.40
    prototype
    -0.39
     galerie
    -0.38
     teil
    -0.38
    IGR
    -0.38
    مراجع
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.95
    oredCriteria
    0.93
    InitVars
    0.91
    sizeCache
    0.87
    Билгалдахарш
    0.85
     BoxDecoration
    0.84
    ThroughAttribute
    0.81
     autorytatywna
    0.81
    tvguidetime
    0.80
    styleType
    0.79
    Activations Density 0.893%

    No Known Activations