© 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. 13062
    Prev
    Next
    INDEX
    Explanations

    the words "oil" and words frequently appearing with oil

    oai_token-act-pair · gemini-2.0-flash

    references to oil

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

    oil

    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
     disambiguazione
    -0.55
    Datuak
    -0.50
    mobileqq
    -0.47
     montagnes
    -0.46
     Efq
    -0.45
     entire
    -0.44
    нского
    -0.44
     khúc
    -0.43
    Requested
    -0.43
    setDefault
    -0.43
    POSITIVE LOGITS
    jsonwebtoken
    0.64
     BitmapFactory
    0.63
    >';
    0.60
    ).</
    0.60
    __":
    0.59
    ScopeManager
    0.59
    AxisAlignment
    0.59
    __':
    0.58
    )}
    0.57
     esternos
    0.57
    Activations Density 1.181%

    No Known Activations