© 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. 13595
    Prev
    Next
    INDEX
    Explanations

    a variety of parenthetical statements and familial relationships

    oai_token-act-pair · gemini-2.0-flash

    tokens with special characters or specific formats

    np_token-act-pair-logits · gpt-4o-mini
    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
     PNC
    -0.70
    SND
    -0.69
    PN
    -0.68
    YN
    -0.67
    HN
    -0.66
    Tn
    -0.63
     PN
    -0.62
     SND
    -0.62
    TNT
    -0.61
    KN
    -0.61
    POSITIVE LOGITS
     MutableLiveData
    0.53
    EDEFAULT
    0.52
    يكب
    0.46
    醐
    0.45
    
    0.45
     Morro
    0.44
    SharedCtor
    0.43
    tplatz
    0.43
    Tembelea
    0.43
     متعلقه
    0.42
    Activations Density 0.907%

    No Known Activations