© 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. 15854
    Prev
    Next
    INDEX
    Explanations

    scientific publications, including author names, journal titles, and publication years

    oai_token-act-pair · gemini-2.0-flash

    and

    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
     and
    -0.92
     from
    -0.85
     or
    -0.82
     at
    -0.80
    -
    -0.80
     on
    -0.77
     for
    -0.75
     in
    -0.72
     is
    -0.67
     with
    -0.64
    POSITIVE LOGITS
     the
    0.79
     co
    0.62
     his
    0.50
     their
    0.49
    djangoproject
    0.48
     other
    0.47
     purpoſe
    0.42
    Portail
    0.41
     some
    0.40
     preſent
    0.39
    Activations Density 8.478%

    No Known Activations