© 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. 6077
    Prev
    Next
    INDEX
    Explanations

    words related to football games and quarterback performance

    oai_token-act-pair · gemini-2.0-flash

    specific types of brands or entities

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

    American football

    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
     End
    -0.63
    End
    -0.62
     Ends
    -0.62
     end
    -0.61
    END
    -0.59
    期刊论文
    -0.58
    ends
    -0.58
    ModelAndView
    -0.58
    Ends
    -0.57
    interopRequire
    -0.57
    POSITIVE LOGITS
     Distrikt
    0.55
    DockStyle
    0.52
    MarshalTo
    0.51
    taza
    0.49
     ADM
    0.48
    Arbitrage
    0.48
     ब्रेकडाउन
    0.47
    etragen
    0.45
    #+#
    0.45
     heli
    0.45
    Activations Density 0.810%

    No Known Activations