© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12065
    Prev
    Next
    INDEX
    Explanations

    punctuation such as quotation marks, parentheses, brackets, greater than/less than symbols, and colons

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     Over
    -1.09
     Back
    -1.06
     After
    -1.03
     Behind
    -1.01
     During
    -1.00
     Later
    -0.99
     Before
    -0.99
     Against
    -0.99
     Following
    -0.99
     Between
    -0.97
    POSITIVE LOGITS
    Styleable
    0.63
    Know
    0.58
    Define
    0.58
    "]="
    0.56
    Are
    0.56
     Are
    0.56
     Czy
    0.54
     Kind
    0.54
     Know
    0.54
     Nice
    0.53
    Activations Density 25.646%

    No Known Activations