© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15086
    Prev
    Next
    INDEX
    Explanations

    instances of "Skill Kyutama" and the superhuman abilities from the show this is from.

    oai_token-act-pair · gemini-2.0-flash

    Kyurangers

    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
     surla
    -0.79
     Exacts
    -0.75
     ainfi
    -0.71
     Efq
    -0.66
     oprot
    -0.66
     المعيارى
    -0.65
     démocratie
    -0.65
     définiti
    -0.64
     vectorielles
    -0.63
     BorderRadius
    -0.60
    POSITIVE LOGITS
     protoimpl
    0.57
     charge
    0.52
    NameInMap
    0.52
     مفص
    0.52
     k
    0.51
     Al
    0.50
    SourceChecksum
    0.47
     CHARGE
    0.47
    فن
    0.46
     disk
    0.46
    Activations Density 6.128%

    No Known Activations