© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4716
    Prev
    Next
    INDEX
    Explanations

    references to the anime series "My Hero Academia"

    oai_token-act-pair · gemini-2.0-flash

    My Hero Academia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     purpoſe
    -0.73
    éroport
    -0.73
    IsMutable
    -0.72
     faſt
    -0.70
    ſelf
    -0.69
     themſelves
    -0.68
     ſtand
    -0.68
     raiſ
    -0.67
    ::_('
    -0.66
     iſt
    -0.65
    POSITIVE LOGITS
    #+#
    0.54
     class
    0.53
     V
    0.52
    yarnpkg
    0.50
    class
    0.49
     Class
    0.46
    Personensuche
    0.44
    V
    0.44
     esternos
    0.44
     CLASS
    0.44
    Activations Density 0.415%

    No Known Activations