© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12126
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or acknowledgement, particularly "well" and "yeah"

    oai_token-act-pair · gemini-2.0-flash

    Well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    TestBed
    -0.64
    ))->
    -0.60
     nakalista
    -0.59
    MessageOf
    -0.58
    enment
    -0.56
    Geografía
    -0.54
    htbp
    -0.54
    Vidite
    -0.54
    cèse
    -0.54
     CreateTagHelper
    -0.52
    POSITIVE LOGITS
    ilaian
    0.54
     autorytatywna
    0.53
    nestjs
    0.52
    }$)
    0.52
    ขึ้น
    0.49
    لينكات
    0.48
    väg
    0.45
     débats
    0.44
    Paypal
    0.44
    ึ้น
    0.44
    Activations Density 1.233%

    No Known Activations