© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12451
    Prev
    Next
    INDEX
    Explanations

    words indicating sentiment, especially the words "positive" and "negative"

    oai_token-act-pair · gemini-2.0-flash

    positive and negative effects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Portail
    -0.68
    pustakaan
    -0.56
    keteers
    -0.54
    bilirsiniz
    -0.53
    rasil
    -0.52
     wensen
    -0.51
     chiare
    -0.51
     sèche
    -0.51
    Charsets
    -0.50
    varargin
    -0.50
    POSITIVE LOGITS
    TagMode
    0.65
    spun
    0.60
     Allociné
    0.54
     Normdatei
    0.54
    ThroughAttribute
    0.52
    fortawesome
    0.52
     esternos
    0.51
    IntoConstraints
    0.49
    Espèce
    0.49
     تضيفلها
    0.48
    Activations Density 4.141%

    No Known Activations