© 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. 12785
    Prev
    Next
    INDEX
    Explanations

    mentions of government authorities and actions, especially arrests and imprisonment, sometimes in the context of historical events.

    oai_token-act-pair · gemini-2.0-flash

    Oppression and authoritarianism

    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
     penal
    -0.55
     penalized
    -0.53
     Référence
    -0.49
    horn
    -0.49
     penalty
    -0.48
     practised
    -0.48
    省市镇
    -0.48
    aben
    -0.48
     prosecution
    -0.48
    iose
    -0.47
    POSITIVE LOGITS
     AspNetCore
    0.70
     saites
    0.65
    TagMode
    0.60
     CGSize
    0.59
     UIKit
    0.57
    stdc
    0.57
     CGPoint
    0.57
    tagHelperRunner
    0.56
    сылкі
    0.56
    enumi
    0.55
    Activations Density 1.987%

    No Known Activations