© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10645
    Prev
    Next
    INDEX
    Explanations

    content related to TV shows, particularly plot summaries and troubled protagonists.

    oai_token-act-pair · gemini-2.0-flash

    superhuman characters/crime 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_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
    MLLoader
    -0.66
    InitVars
    -0.64
     étrangère
    -0.56
     preghiera
    -0.54
     vacanze
    -0.52
     touristes
    -0.52
     dépens
    -0.52
     varandra
    -0.52
     onlyOwner
    -0.51
    providedIn
    -0.51
    POSITIVE LOGITS
     للاسماء
    0.63
    BagConstraints
    0.61
     الحره
    0.51
    licone
    0.50
    RTEX
    0.50
     MI
    0.48
     war
    0.48
     brilliance
    0.47
     مشين
    0.47
     cy
    0.47
    Activations Density 4.727%

    No Known Activations