© 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. 11967
    Prev
    Next
    INDEX
    Explanations

    prepositions and words that commonly surround them

    oai_token-act-pair · gemini-2.0-flash

    Being inside a location

    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
     otomatig
    -0.74
    الإنجليزية
    -0.74
    extAlignment
    -0.72
     pylint
    -0.70
     beginnetje
    -0.68
     שוליים
    -0.66
     Himo
    -0.65
     دیکھیے
    -0.65
     تانيه
    -0.64
     PopupWindow
    -0.64
    POSITIVE LOGITS
    AndroidJUnit
    0.42
    straints
    0.40
    hobia
    0.36
    migrationBuilder
    0.35
    contentLoaded
    0.35
    żeń
    0.35
    исленность
    0.35
     labourers
    0.34
    hey
    0.34
    hearsal
    0.33
    Activations Density 6.138%

    No Known Activations