© 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. 13275
    Prev
    Next
    INDEX
    Explanations

    text from online gaming forums or similar environments, responding to announcements or rule postings

    oai_token-act-pair · gemini-2.0-flash

    online comments

    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
     utafiti
    -0.49
     électroniques
    -0.46
     passés
    -0.44
     supérieurs
    -0.44
     Weltkrieg
    -0.43
     rendus
    -0.42
     deudas
    -0.42
     InputDecoration
    -0.41
     définiti
    -0.41
     dégust
    -0.40
    POSITIVE LOGITS
    LookAnd
    0.87
     recens
    0.62
     Picchu
    0.59
     препратки
    0.58
     played
    0.58
     Played
    0.57
     RECORD
    0.57
    ()]
    0.56
     Playing
    0.56
     record
    0.56
    Activations Density 6.754%

    No Known Activations