© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13675
    Prev
    Next
    INDEX
    Explanations

    words that include the strings 'key', 'string' or 'panel' in various contexts.

    oai_token-act-pair · gemini-2.0-flash

    key

    np_max-act · gemini-2.0-flash

    key

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     key
    -2.02
     keys
    -1.88
     Key
    -1.79
    key
    -1.72
    Key
    -1.69
     KEY
    -1.67
     Keys
    -1.57
    KEY
    -1.49
    keys
    -1.47
     KEYS
    -1.45
    POSITIVE LOGITS
     bőr
    0.49
     Vikipedi
    0.49
     történ
    0.46
    postsleuth
    0.46
     Ouv
    0.45
     megjelen
    0.44
    opsida
    0.44
    miyorum
    0.43
     समीक्षक
    0.43
     yaş
    0.43
    Activations Density 24.681%

    No Known Activations