© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8333
    Prev
    Next
    INDEX
    Explanations

    references to TV shows and movies

    oai_token-act-pair · gemini-2.0-flash

    Movies and TV shows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    DeleteBehavior
    -0.94
    تقاوى
    -0.93
     pinulongan
    -0.91
    mybatisplus
    -0.90
    rungsseite
    -0.87
     '\\;'
    -0.86
    migrationBuilder
    -0.86
     Majefty
    -0.84
     Jefus
    -0.83
     Wicidata
    -0.82
    POSITIVE LOGITS
     Meets
    0.46
     Meet
    0.44
     Two
    0.39
    :
    0.39
     Overcome
    0.38
     Three
    0.38
     Back
    0.36
     orígenes
    0.36
     CreateTagHelper
    0.36
     Set
    0.36
    Activations Density 9.740%

    No Known Activations