© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    words related to ability and negative conditions

    oai_token-act-pair · gemini-2.0-flash

    capable or dirty

    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
     ModelExpression
    -0.76
     AssemblyCulture
    -0.70
     CMB
    -0.68
     Amadeus
    -0.67
     TSH
    -0.66
     OSS
    -0.65
     bellows
    -0.64
     fermés
    -0.64
     PLW
    -0.64
     IAC
    -0.62
    POSITIVE LOGITS
     the
    0.74
    %");
    0.68
    Ữ
    0.68
    íslu
    0.67
    proken
    0.65
     محفوظة
    0.65
    BRARY
    0.65
    ILDREN
    0.63
    IDATE
    0.63
     Schmel
    0.62
    Activations Density 1.855%

    No Known Activations