© 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. 13088
    Prev
    Next
    INDEX
    Explanations

    descriptions of architectural details, especially in churches

    oai_token-act-pair · gemini-2.0-flash

    glass

    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
     виправивши
    -0.78
    NUMX
    -0.73
    SharedDtor
    -0.71
    abestanden
    -0.71
    olesale
    -0.69
    SourceChecksum
    -0.68
    intios
    -0.67
     مرئيه
    -0.66
     myſelf
    -0.63
    protoimpl
    -0.62
    POSITIVE LOGITS
     True
    0.50
    True
    0.48
    ėl
    0.46
    ciences
    0.44
    حت
    0.42
    捐
    0.42
     self
    0.42
     abgerufen
    0.41
    nių
    0.41
     might
    0.40
    Activations Density 0.798%

    No Known Activations