© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14375
    Prev
    Next
    INDEX
    Explanations

    the word "valid" and words relating to pressing a button or news

    oai_token-act-pair · gemini-2.0-flash

    valid

    np_max-act · gemini-2.0-flash

    valid

    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
    AndEndTag
    -0.94
    ISupport
    -0.94
     дописавши
    -0.82
    webElementGuid
    -0.82
     &___
    -0.82
    featureID
    -0.81
    
    -0.80
    TypedDataSet
    -0.77
    writeFieldEnd
    -0.75
    HasForeignKey
    -0.75
    POSITIVE LOGITS
    ?")
    0.58
    "):
    0.53
    們
    0.53
    BinaryTree
    0.51
    anjutan
    0.48
    ?')
    0.47
    tably
    0.47
    ilaire
    0.47
    Lịch
    0.47
    !")
    0.47
    Activations Density 0.350%

    No Known Activations