© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14312
    Prev
    Next
    INDEX
    Explanations

    geographic names and associated political entities, perhaps also names and titles

    oai_token-act-pair · gemini-2.0-flash

    words related to political struggles and events

    np_token-act-pair-logits · gpt-4o-mini

    War and political conflict

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    #
    -0.66
     Familienname
    -0.59
     paraître
    -0.59
    <?
    -0.58
     asiatique
    -0.58
    蚪
    -0.56
     explí
    -0.54
     <<<<<<<<<<<<<<
    -0.54
    hoeddwyd
    -0.52
     enseña
    -0.52
    POSITIVE LOGITS
     exter
    0.52
    gain
    0.50
     holo
    0.50
     unification
    0.49
     EXTER
    0.49
     gain
    0.49
     unite
    0.48
    VINCE
    0.47
     invaded
    0.47
     chancellor
    0.46
    Activations Density 4.863%

    No Known Activations