© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9440
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to access, security, and operating a gate or door, often key-related.

    oai_token-act-pair · gemini-2.0-flash

    Security and access

    np_max-act · gemini-2.0-flash

    locks and keys

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    gued
    -0.55
    abetes
    -0.49
    displayquote
    -0.46
     नव
    -0.45
    sbin
    -0.45
    xnn
    -0.44
    popular
    -0.44
    人気
    -0.43
    Cite
    -0.43
     popular
    -0.43
    POSITIVE LOGITS
    LookAnd
    0.63
     "..\..\
    0.63
    anskje
    0.61
    gameserver
    0.58
    WithMany
    0.57
    CppCodeGen
    0.56
    IndentedString
    0.56
     iprot
    0.56
    principalColumn
    0.56
    })`
    0.55
    Activations Density 0.710%

    No Known Activations