© 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. 2758
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to film criticism and negative political commentary

    oai_token-act-pair · gemini-2.0-flash

    Reviews and descriptions

    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
    WireFormatLite
    -0.61
    ImageContext
    -0.52
    ⓧ
    -0.51
    Hochspringen
    -0.50
    vsk
    -0.50
    GraphicsUnit
    -0.50
    WriteBarrier
    -0.49
    Portale
    -0.47
    kloped
    -0.47
    NORE
    -0.46
    POSITIVE LOGITS
    曖昧さ回避
    0.73
     Personne
    0.60
    getPrice
    0.60
     TextAppearance
    0.58
    ebenarnya
    0.57
    }{*}{
    0.57
     Dernière
    0.56
    듈
    0.56
     personne
    0.56
    Persons
    0.55
    Activations Density 13.045%

    No Known Activations