© 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. 4020
    Prev
    Next
    INDEX
    Explanations

    decimal numbers

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming syntax

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

    math problems

    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
    ']")
    -0.65
     })}
    -0.62
     argint
    -0.56
     pinulongan
    -0.56
    }(),
    -0.55
     siihen
    -0.54
    tymologie
    -0.52
    }`}
    -0.52
     ſta
    -0.52
    `]
    -0.52
    POSITIVE LOGITS
    spesies
    0.64
    DebuggerNonUser
    0.63
     MainAxisSize
    0.63
    AndEndTag
    0.61
    SOUNDBITE
    0.58
     ModelExpression
    0.56
    DockStyle
    0.56
     kasarigan
    0.54
     Attribution
    0.53
     }{@
    0.53
    Activations Density 2.037%

    No Known Activations