© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16200
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act · gemini-2.0-flash

    :

    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
    :
    -3.48
     :
    -1.42
    :
    -1.34
    ,
    -1.33
    ;
    -1.26
    ：
    -1.23
    :}
    -1.17
    :</
    -1.16
    :.
    -1.14
    :\
    -1.11
    POSITIVE LOGITS
     myſelf
    1.59
     itſelf
    1.53
     ſeveral
    1.52
     Monfieur
    1.48
     Houſe
    1.47
     himſelf
    1.46
     Reſ
    1.45
     Theſe
    1.45
     themſelves
    1.43
    OGND
    1.42
    Activations Density 1.691%

    No Known Activations