© 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. 10498
    Prev
    Next
    INDEX
    Explanations

    words related to common problems or issues in games and relationships

    oai_token-act-pair · 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
     disambiguazione
    -0.97
     réguli
    -0.73
     démocr
    -0.67
    saraba
    -0.67
    ########.
    -0.67
    
    -0.67
     complètes
    -0.65
     vägen
    -0.63
     مشين
    -0.61
     commerciales
    -0.61
    POSITIVE LOGITS
    estination
    0.52
    esterol
    0.52
    ownload
    0.51
     sounds
    0.49
    fucker
    0.48
     endfor
    0.48
     Normandy
    0.48
     Brill
    0.47
     Claudius
    0.47
    تقاوى
    0.47
    Activations Density 6.734%

    No Known Activations