© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9275
    Prev
    Next
    INDEX
    Explanations

    words commonly associated with finance and governmental regulation.

    oai_token-act-pair · gemini-2.0-flash

    accounting terms and standards

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

    accounting and audits

    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
    EndContext
    -0.76
     createState
    -0.71
    
    -0.65
    sidemargin
    -0.65
    deelte
    -0.62
     okuyayım
    -0.61
    TagMode
    -0.59
     _$
    -0.56
     dB
    -0.55
    "';
    -0.54
    POSITIVE LOGITS
     AS
    0.63
    AS
    0.56
     Statement
    0.54
    SharedDtor
    0.51
    enterOuterAlt
    0.49
    nas
    0.48
    EndGlobalSection
    0.48
     FAS
    0.48
    ASC
    0.47
     fe
    0.46
    Activations Density 2.148%

    No Known Activations