© 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. 10729
    Prev
    Next
    INDEX
    Explanations

    technical and professional contexts, including science and technology fields

    oai_token-act-pair · gemini-2.0-flash

    two letter acronyms

    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
    Referencies
    -0.47
     HIEROGLYPH
    -0.44
     CALIFORNI
    -0.44
    sự
    -0.43
    曖昧さ回避
    -0.42
    mặt
    -0.42
    ALREADY
    -0.42
    OBJET
    -0.42
    ation
    -0.42
    REDIS
    -0.40
    POSITIVE LOGITS
    F
    0.79
    FC
    0.77
    PF
    0.75
    PP
    0.74
    CF
    0.74
    LC
    0.73
    BC
    0.72
    FT
    0.72
    SS
    0.72
    CC
    0.71
    Activations Density 66.042%

    No Known Activations