© 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. 11114
    Prev
    Next
    INDEX
    Explanations

    code snippets or licensing information

    oai_token-act-pair · gemini-2.0-flash

    Software licenses and disclaimers

    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
    AndEndTag
    -0.63
     Straight
    -0.61
     Pure
    -0.58
     autorytatywna
    -0.58
     Slow
    -0.58
     Moderate
    -0.57
    EndContext
    -0.57
     Minimal
    -0.56
    Pure
    -0.55
     Easy
    -0.55
    POSITIVE LOGITS
     تضيفلها
    0.67
     CreateTagHelper
    0.52
     credere
    0.45
    Diwedd
    0.45
    holy
    0.42
     right
    0.40
    putable
    0.40
     holy
    0.39
     short
    0.39
    thargy
    0.38
    Activations Density 7.135%

    No Known Activations