© 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. 6311
    Prev
    Next
    INDEX
    Explanations

    Latex code, especially formulas with specific characters like backslashes, curly braces, and Greek letters.

    oai_token-act-pair · gemini-2.0-flash

    say "right"

    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
     auffi
    -0.65
     tranſ
    -0.57
     ſtre
    -0.57
     diſt
    -0.55
     westfalen
    -0.55
    interopRequire
    -0.54
     málaga
    -0.54
     Monfieur
    -0.54
     eſſ
    -0.53
     Ayuda
    -0.53
    POSITIVE LOGITS
    right
    0.78
    lceil
    0.52
    rangle
    0.49
     right
    0.49
    end
    0.48
    :**
    0.47
    PasswordEncoder
    0.46
    llong
    0.46
    ]]>
    0.45
    ].)
    0.45
    Activations Density 1.703%

    No Known Activations