© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13355
    Prev
    Next
    INDEX
    Explanations

    words related to religious and social systems, or the act of institutionalization

    oai_token-act-pair · gemini-2.0-flash

    academic/religious texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Hentet
    -0.65
     propOrder
    -0.59
     ostavi
    -0.58
    ьаж
    -0.54
     RouterModule
    -0.52
    MessageTagHelper
    -0.52
     صوتيه
    -0.50
     blessures
    -0.48
     esternos
    -0.47
    enterOuterAlt
    -0.47
    POSITIVE LOGITS
     مشين
    0.68
     τὸν
    0.63
     bound
    0.60
    endforeach
    0.60
    mentary
    0.59
     متعلقه
    0.58
     imb
    0.57
    UserScript
    0.56
     plugged
    0.54
    HostException
    0.54
    Activations Density 7.227%

    No Known Activations