© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10467
    Prev
    Next
    INDEX
    Explanations

    short informational paragraphs followed by a blank space.

    oai_token-act-pair · gemini-2.0-flash

    Internet forum content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    enderror
    -0.63
    arraycopy
    -0.61
    TagHelper
    -0.56
    TintMode
    -0.56
    WebVitals
    -0.55
     tóxic
    -0.55
    HasOne
    -0.54
     parseFrom
    -0.54
     consultato
    -0.54
    gdx
    -0.53
    POSITIVE LOGITS
     nakalista
    0.70
     يتيمه
    0.62
     obicei
    0.61
     picioare
    0.61
    nosaurus
    0.59
    bibinfo
    0.57
    ertale
    0.57
    bibfield
    0.56
    MockMvc
    0.56
    XMLSchema
    0.56
    Activations Density 1.922%

    No Known Activations