© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12971
    Prev
    Next
    INDEX
    Explanations

    mentions of snow and related terms like packs and earth.

    oai_token-act-pair · gemini-2.0-flash

    snow

    np_max-act · gemini-2.0-flash

    ▁snow

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Headset
    -0.60
    DOCTYPE
    -0.57
    emias
    -0.57
     Undeclared
    -0.56
    SEGU
    -0.55
    pausal
    -0.54
    rentices
    -0.54
    alate
    -0.54
    FieldBuilder
    -0.54
    DeleteBehavior
    -0.53
    POSITIVE LOGITS
    <bos>
    2.19
    '
    0.64
    basicConfig
    0.63
    ’
    0.61
     onCreateView
    0.55
    awtextra
    0.53
    onViewCreated
    0.53
    “
    0.52
    GetMapping
    0.52
     BoxDecoration
    0.49
    Activations Density 0.695%

    No Known Activations