© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9455
    Prev
    Next
    INDEX
    Explanations

    words expressing personal sentiment or opinions about media

    oai_token-act-pair · gemini-2.0-flash

    expressing emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     @"/
    -0.74
     MainAxisSize
    -0.73
    SourceChecksum
    -0.68
    بوابة
    -0.64
    SPATH
    -0.64
    uxxxx
    -0.60
     softmax
    -0.60
    ombie
    -0.60
    enderror
    -0.59
     MAF
    -0.58
    POSITIVE LOGITS
     kanyang
    0.50
    inander
    0.49
     uns
    0.45
     sepen
    0.45
    Havolalar
    0.45
    música
    0.43
    rxjs
    0.43
    srand
    0.42
    الان
    0.41
    тербург
    0.40
    Activations Density 2.347%

    No Known Activations