© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12517
    Prev
    Next
    INDEX
    Explanations

    a jumbled mess of seemingly random words having something to do with the word "the".

    oai_token-act-pair · gemini-2.0-flash

    fantasy/sci-fi narratives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ::~
    -0.46
    GenerationType
    -0.42
    Autowired
    -0.41
    IBOutlet
    -0.41
     gekomen
    -0.40
    Kit
    -0.39
     كومونز
    -0.39
     hjälp
    -0.38
    Aid
    -0.38
    tischer
    -0.38
    POSITIVE LOGITS
    +#+
    0.88
    ########.
    0.84
    AnimationsModule
    0.81
     purpoſe
    0.76
     themſelves
    0.73
     Anſ
    0.72
     itſelf
    0.71
     utafitiHapana
    0.71
     ſtate
    0.71
     perſon
    0.71
    Activations Density 3.305%

    No Known Activations