© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2611
    Prev
    Next
    INDEX
    Explanations

    sentences that express an opinion or assessment about a current state

    oai_token-act-pair · gemini-2.0-flash

    expressing a state of being

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     EconPapers
    -0.68
    hyrchwyd
    -0.68
    esez
    -0.60
    LLocation
    -0.56
    saraba
    -0.54
    Pozri
    -0.54
    Vezi
    -0.54
    endpush
    -0.52
    writerow
    -0.50
    Geplaatst
    -0.49
    POSITIVE LOGITS
    archiviato
    0.52
     cromado
    0.51
    ersdorf
    0.50
     NIA
    0.49
    Архівовано
    0.49
    DBNull
    0.49
     sandero
    0.48
     ſta
    0.48
     inoxid
    0.48
     تضيفلها
    0.48
    Activations Density 2.720%

    No Known Activations