© 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. 5826
    Prev
    Next
    INDEX
    Explanations

    crime-related words and phrases, especially those relating to violence, theft, legal processes, and accusations.

    oai_token-act-pair · gemini-2.0-flash

    break

    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
    SaveChangesAsync
    -0.58
    bewerken
    -0.57
     createState
    -0.57
     يتيمه
    -0.55
    Rhestr
    -0.54
     ceded
    -0.51
    ">—
    -0.49
    alom
    -0.48
    Mutant
    -0.48
    thenReturn
    -0.47
    POSITIVE LOGITS
     break
    1.52
    break
    1.38
     Break
    1.33
    Break
    1.23
     breaking
    1.16
     BREAK
    1.09
     breaks
    1.09
    breaking
    1.03
    BREAK
    1.01
     broke
    0.98
    Activations Density 2.093%

    No Known Activations