© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16364
    Prev
    Next
    INDEX
    Explanations

    something like "a hill" or "near the"

    oai_token-act-pair · gemini-2.0-flash

    scenery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     plazas
    -0.63
     pits
    -0.62
     holes
    -0.62
     squares
    -0.60
     ditches
    -0.60
     shade
    -0.57
     corners
    -0.55
     niches
    -0.55
     Beaches
    -0.55
    󠁢
    -0.54
    POSITIVE LOGITS
     صوتيه
    0.58
     propOrder
    0.57
    Foods
    0.56
    يميديا
    0.53
    yntaxException
    0.52
     foods
    0.51
    原神
    0.51
    انجليز
    0.50
    djangoproject
    0.50
    SerializedSize
    0.50
    Activations Density 5.363%

    No Known Activations