© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5552
    Prev
    Next
    INDEX
    Explanations

    what looks like chemical or brand names

    oai_token-act-pair · gemini-2.0-flash

    ery

    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
    DockStyle
    -0.71
    ChildScrollView
    -0.65
    enumii
    -0.58
     Roskov
    -0.58
    icoot
    -0.56
    UnusedPrivate
    -0.56
    IsContent
    -0.51
     ModelExpression
    -0.50
     Teich
    -0.49
    dotenv
    -0.49
    POSITIVE LOGITS
    cyjne
    0.68
    igraphy
    0.66
    cyjny
    0.65
    flage
    0.63
    acyjny
    0.62
    acyjne
    0.59
    cyjna
    0.54
    cjach
    0.53
     tombé
    0.49
     cober
    0.49
    Activations Density 1.832%

    No Known Activations