© 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. 12406
    Prev
    Next
    INDEX
    Explanations

    product features listed with bullet points

    oai_token-act-pair · gemini-2.0-flash

    Product descriptions

    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
    ReusableCell
    -0.88
    DockStyle
    -0.79
    forChild
    -0.77
    TagMode
    -0.73
    PerformLayout
    -0.72
    XmlAccessType
    -0.71
    +#+#
    -0.71
     houſe
    -0.68
    AndEndTag
    -0.68
     AssemblyCulture
    -0.67
    POSITIVE LOGITS
     Ne
    0.47
    Ne
    0.46
    Init
    0.44
     kere
    0.43
     ne
    0.43
    AppMethodBeat
    0.41
     sein
    0.39
    li
    0.39
     li
    0.39
     My
    0.38
    Activations Density 2.102%

    No Known Activations