© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12611
    Prev
    Next
    INDEX
    Explanations

    the word "alternative"

    oai_token-act-pair · gemini-2.0-flash

    alternative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     morire
    -0.98
     ModelExpression
    -0.91
     CreateTagHelper
    -0.91
     spesa
    -0.90
     préc
    -0.89
     déclar
    -0.89
     grazia
    -0.89
     stället
    -0.88
     spese
    -0.88
     giustizia
    -0.85
    POSITIVE LOGITS
     concept
    0.67
     full
    0.61
     typically
    0.60
    able
    0.59
     traditional
    0.58
     via
    0.57
     %>
    0.57
    разуме
    0.56
     meaning
    0.56
     specific
    0.56
    Activations Density 1.541%

    No Known Activations