© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3310
    Prev
    Next
    INDEX
    Explanations

    uses of the first person to introduce opinion or analysis

    oai_token-act-pair · gemini-2.0-flash

    Avoiding/stopping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     թվական
    -0.54
    "?>
    -0.50
    flashdata
    -0.49
    oursquare
    -0.48
     betweenstory
    -0.47
    ритори
    -0.45
     spé
    -0.44
    romatic
    -0.44
     unange
    -0.43
    はじめに
    -0.42
    POSITIVE LOGITS
     desist
    1.23
     refra
    1.05
     abstain
    1.02
     abstinence
    1.02
     absten
    0.96
     refrain
    0.92
     forbear
    0.82
     withdrawal
    0.81
     quit
    0.81
     renounced
    0.81
    Activations Density 3.675%

    No Known Activations