© 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. 6818
    Prev
    Next
    INDEX
    Explanations

    code blocks that are either opening, have multiple '$handler->handle', or have multiple assertions

    oai_token-act-pair · gemini-2.0-flash

    code and logs

    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
     Efq
    -1.59
     myſelf
    -1.55
     Theſe
    -1.52
     propOrder
    -1.52
     ―――――
    -1.50
     itſelf
    -1.49
     Jefus
    -1.42
    AndEndTag
    -1.41
     himſelf
    -1.41
    NUMX
    -1.41
    POSITIVE LOGITS
    <unused61>
    0.16
    <unused62>
    0.13
    <unused63>
    0.13
    l
    0.11
    <0xE1>
    0.10
    par
    0.10
    <unused60>
    0.08
    â
    0.08
    un
    0.07
    ma
    0.07
    Activations Density 1.356%

    No Known Activations