© 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. 12907
    Prev
    Next
    INDEX
    Explanations

    mentions of the Stack Exchange network or Stack Overflow

    oai_token-act-pair · gemini-2.0-flash

    stack

    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
     stack
    -2.25
     Stack
    -2.09
     stacks
    -2.03
    Stack
    -2.03
    stack
    -1.98
     STACK
    -1.97
     stacking
    -1.91
     stacked
    -1.86
    STACK
    -1.85
     Stacks
    -1.83
    POSITIVE LOGITS
    neman
    0.49
     SwitchCompat
    0.48
     paroles
    0.46
    spath
    0.46
     Nationalist
    0.46
    InteropServices
    0.46
    ěř
    0.45
     Zephyr
    0.45
    riturismo
    0.44
     ZH
    0.44
    Activations Density 1.127%

    No Known Activations