© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8888
    Prev
    Next
    INDEX
    Explanations

    mentions of television shows related to A&E network, with emphasis on season premieres and viewership numbers

    oai_token-act-pair · gemini-2.0-flash

    fragments of words

    np_token-act-pair-logits · gpt-4o-mini

    TV show season/episode

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     HasFactory
    -0.98
     itſelf
    -0.89
     Majefty
    -0.88
     pleaſure
    -0.88
     themſelves
    -0.85
     leaſt
    -0.84
     nakalista
    -0.84
     fhew
    -0.84
     صوتيه
    -0.84
     initComponents
    -0.81
    POSITIVE LOGITS
    leg
    0.44
    ie
    0.40
     a
    0.40
    ib
    0.40
     star
    0.39
     se
    0.39
    fil
    0.39
     twice
    0.39
     as
    0.39
    ja
    0.38
    Activations Density 2.962%

    No Known Activations