© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12517
    Prev
    Next
    INDEX
    Explanations

    mentions of noses alongside a variety of other concepts, including dogs, injury, and internet posts, but the common thread appears to be a focus on interaction and detection

    oai_token-act-pair · gemini-2.0-flash

    nose

    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
     Efq
    -2.17
     photolibrary
    -2.13
     myſelf
    -2.06
     Majefty
    -2.05
     Monfieur
    -1.94
     Theſe
    -1.91
     Forumite
    -1.91
     $_"
    -1.85
     feroit
    -1.83
     Jefus
    -1.82
    POSITIVE LOGITS
     to
    1.27
     and
    1.23
     in
    1.22
     
    1.20
     "
    1.20
     (
    1.16
    ↵
    1.16
    .
    1.15
    ,
    1.14
     of
    1.13
    Activations Density 3.468%

    No Known Activations