© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5233
    Prev
    Next
    INDEX
    Explanations

    language related to religion, spirituality, injustice or social class

    oai_token-act-pair · gemini-2.0-flash

    Abstract concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     دیکھیے
    -0.54
    photobucket
    -0.54
    AxisAlignment
    -0.53
    cestershire
    -0.52
     onOptions
    -0.51
    EndGlobalSection
    -0.50
    ArrowToggle
    -0.47
    NAF
    -0.47
    SerializedSize
    -0.47
    ècie
    -0.46
    POSITIVE LOGITS
     Équipe
    0.60
    Clue
    0.54
     Ener
    0.53
    Ener
    0.52
    EDEFAULT
    0.51
    oretical
    0.50
     Incenti
    0.50
     Addressing
    0.49
     Slade
    0.49
     Influences
    0.49
    Activations Density 26.999%

    No Known Activations