© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13388
    Prev
    Next
    INDEX
    Explanations

    capital letters, particularly C and D, that often begin a word or acronym

    oai_token-act-pair · gemini-2.0-flash

    C and D

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SourceChecksum
    -0.66
     sockaddr
    -0.60
    
    -0.59
    brainly
    -0.58
     decorativas
    -0.57
     plotly
    -0.52
    onOptions
    -0.52
    Investments
    -0.51
    ValueGenerated
    -0.50
     decorativa
    -0.50
    POSITIVE LOGITS
    principalColumn
    0.57
    {}\
    0.49
    haka
    0.45
    manos
    0.45
    ows
    0.45
    OPE
    0.45
    }))
    0.45
    enten
    0.43
    aly
    0.43
    [];
    0.43
    Activations Density 0.232%

    No Known Activations