© 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. 11360
    Prev
    Next
    INDEX
    Explanations

    the word "subjects," often in a medical or scientific context and sometimes accompanied by adjectives

    oai_token-act-pair · gemini-2.0-flash

    subjects

    np_max-act · gemini-2.0-flash

    subjects

    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
    AndEndTag
    -0.71
     ModelExpression
    -0.65
     AssemblyCulture
    -0.65
    AnchorStyles
    -0.64
    AddTagHelper
    -0.64
    󠁴
    -0.63
    esModule
    -0.63
     serviceName
    -0.62
    MessageOf
    -0.61
    tadır
    -0.60
    POSITIVE LOGITS
    <bos>
    1.38
     espagne
    0.58
     auffi
    0.57
     children
    0.56
     quæ
    0.56
     perſon
    0.54
     patients
    0.52
     maroca
    0.51
     kids
    0.51
     ainfi
    0.50
    Activations Density 1.852%

    No Known Activations