© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13939
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with negative, potentially dangerous, situations or outcomes.

    oai_token-act-pair · gemini-2.0-flash

    problems and issues

    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
     grail
    -0.54
    DropColumn
    -0.52
    TestBed
    -0.52
    DataSnapshot
    -0.52
     Oli
    -0.51
    ErrUnexpectedEOF
    -0.51
    orsese
    -0.51
    afficheront
    -0.50
     Bowman
    -0.50
    DoubleQuotes
    -0.50
    POSITIVE LOGITS
     defaultstate
    0.68
     reared
    0.60
     bite
    0.60
     rear
    0.60
    Hau
    0.56
    bite
    0.56
     rearing
    0.54
     haunted
    0.54
    rear
    0.53
     Hau
    0.52
    Activations Density 3.742%

    No Known Activations