© 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. 16164
    Prev
    Next
    INDEX
    Explanations

    years in the 2000s and 2010s

    oai_token-act-pair · gemini-2.0-flash

    News and blog posts

    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
    Jereo
    -0.71
     ContentValues
    -0.60
    +");
    -0.58
    المناصب
    -0.57
    expandindo
    -0.56
    руппа
    -0.55
    =*
    -0.54
    /*",
    -0.54
     chande
    -0.54
     AssemblyCulture
    -0.53
    POSITIVE LOGITS
    Mys
    0.51
    InSection
    0.48
    étr
    0.47
    ELTS
    0.46
    URBANA
    0.44
    dsk
    0.44
     Edg
    0.44
    ENDING
    0.44
     Dalai
    0.43
    Kok
    0.43
    Activations Density 7.298%

    No Known Activations