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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6051
    Prev
    Next
    INDEX
    Explanations

    periods, spaces, and the number 1

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash

    . Method used: 1 — reason: MAX_ACTIVATING_TOKENS are all periods — explanation:

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    .
    -5.19
    ,
    -3.80
     
    -3.53
     (
    -3.31
    -
    -3.23
    :
    -2.97
     in
    -2.84
    ;
    -2.83
    /
    -2.81
    (
    -2.72
    POSITIVE LOGITS
     myſelf
    6.38
     Efq
    6.38
     itſelf
    6.09
     Monfieur
    5.91
     Theſe
    5.78
     Jefus
    5.59
     Majefty
    5.53
     ―――――
    5.47
     Houſe
    5.41
     ſeveral
    5.38
    Activations Density 5.694%

    No Known Activations