© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    the stemmed word "reason" plus words about elements, final orders, groups, or someone named Hart

    oai_token-act-pair · gemini-2.0-flash

    reason

    np_max-act · gemini-2.0-flash
    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
     deſt
    -1.17
     purpoſe
    -1.16
     reaſon
    -1.14
     myſelf
    -1.14
    ^(@)
    -1.13
     anſ
    -1.12
     snippetHide
    -1.11
    ISupport
    -1.11
     faſt
    -1.09
     uſ
    -1.06
    POSITIVE LOGITS
    ↵↵
    0.78
    5
    0.75
    2
    0.75
     the
    0.75
    3
    0.72
     and
    0.71
    1
    0.70
    4
    0.65
    L
    0.65
    6
    0.64
    Activations Density 1.706%

    No Known Activations