© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6229
    Prev
    Next
    INDEX
    Explanations

    location words and prepositions

    oai_token-act-pair · gemini-2.0-flash

    irregular syntax and programming patterns

    np_token-act-pair-logits · gpt-4o-mini

    describing locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     CreateTagHelper
    -0.83
     ब्रेकडाउन
    -0.59
     transfieras
    -0.53
    MessageTagHelper
    -0.52
     flake
    -0.52
     Czę
    -0.51
     Accelerated
    -0.51
    NegativeButton
    -0.51
    +:+
    -0.50
    ThemeOverlay
    -0.50
    POSITIVE LOGITS
     getRule
    0.53
    ]){
    0.51
    ]))
    0.51
    marle
    0.50
    ίναι
    0.49
    <?
    0.49
     =>
    0.48
    OLDER
    0.48
    buttonShape
    0.48
    holdings
    0.47
    Activations Density 0.858%

    No Known Activations