© 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. 11945
    Prev
    Next
    INDEX
    Explanations

    references to film criticism, specifically complaining about jump scares and loud noises in horror movies

    oai_token-act-pair · gemini-2.0-flash

    ,

    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
    SharedDtor
    -0.67
    rrggbb
    -0.59
    tonsoft
    -0.58
    Xna
    -0.58
    Rhestr
    -0.57
    rhosis
    -0.53
    AndEndTag
    -0.50
     pinulongan
    -0.49
     gynhyrchwyd
    -0.48
    httphttps
    -0.47
    POSITIVE LOGITS
    piram
    0.59
    fitri
    0.56
    ceğini
    0.54
    èdia
    0.52
     карьер
    0.52
     ostavi
    0.49
    wantErr
    0.48
    shiro
    0.48
     CARR
    0.48
    لاث
    0.47
    Activations Density 1.726%

    No Known Activations