© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10612
    Prev
    Next
    INDEX
    Explanations

    words ending in "hts" or containing "c<some character that is not a-z or A-Z>ment", or containing "ometry", as well as single letter h or digraph AK.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Gim
    -0.71
     Winaray
    -0.65
     Proper
    -0.64
    ագրություններ
    -0.63
     Gim
    -0.63
    rouch
    -0.61
     uintptr
    -0.59
     Latency
    -0.58
    proper
    -0.58
     AspNetCore
    -0.57
    POSITIVE LOGITS
     power
    1.55
    power
    1.38
     Power
    1.33
     strength
    1.31
    Power
    1.30
    POWER
    1.21
     POWER
    1.20
    strength
    1.20
     Strength
    1.17
    Strength
    1.17
    Activations Density 0.616%

    No Known Activations