© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10782
    Prev
    Next
    INDEX
    Explanations

    comparatives used to describe societal trends or behavior

    oai_token-act-pair · gemini-2.0-flash

    sub/counter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Obrador
    -0.56
    patine
    -0.51
     liné
    -0.51
     défaite
    -0.50
    SerializedSize
    -0.49
     fondi
    -0.49
    Vidite
    -0.48
    Method
    -0.47
     Púb
    -0.47
     gewonnen
    -0.47
    POSITIVE LOGITS
     sub
    1.31
     counter
    1.08
    sub
    1.04
    counter
    0.94
     Sub
    0.93
    Sub
    0.91
     Counter
    0.80
    SUB
    0.80
     суб
    0.79
    サブ
    0.79
    Activations Density 3.425%

    No Known Activations