© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8637
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical conditions and anatomy

    oai_token-act-pair · gemini-2.0-flash

    body and anatomy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ImageContext
    -0.86
     OFDb
    -0.86
    rungsseite
    -0.85
     lenker
    -0.85
    IVEREF
    -0.83
     betweenstory
    -0.80
     snippetHide
    -0.80
     समीक्षाओं
    -0.79
     consultato
    -0.78
    évaluateur
    -0.78
    POSITIVE LOGITS
     soft
    0.36
    L
    0.35
    GetKeyDown
    0.34
    multicolumn
    0.33
     vis
    0.32
    GI
    0.32
    sw
    0.32
    aba
    0.32
    Soft
    0.31
     Gu
    0.31
    Activations Density 3.650%

    No Known Activations