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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10087
    Prev
    Next
    INDEX
    Explanations

    words related to Japanese fictional characters, especially in the context of a series or media franchise.

    oai_token-act-pair · gemini-2.0-flash

    Japanese show script

    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
    awaiter
    -0.88
    StoryboardSegue
    -0.76
    VolleyError
    -0.74
    tagHelperRunner
    -0.73
    twimg
    -0.71
     doInBackground
    -0.70
    httphttps
    -0.70
     OnTriggerEnter
    -0.69
    <bos>
    -0.69
    verifyException
    -0.68
    POSITIVE LOGITS
    Personensuche
    0.41
     aspirant
    0.37
     officers
    0.36
     officer
    0.36
     seekers
    0.36
    Power
    0.36
    officers
    0.35
     kính
    0.34
     Pública
    0.33
     Ayuntamiento
    0.33
    Activations Density 1.451%

    No Known Activations