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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1042
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations relating to legal proceedings, locations, and dates

    oai_token-act-pair · gemini-2.0-flash

    is

    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
    RegressionTest
    -0.54
     kasarigan
    -0.53
     XNUMX
    -0.51
     ‡
    -0.50
    ]")]
    -0.50
    AutoScale
    -0.49
    AccessorTable
    -0.49
    LLocation
    -0.47
     snd
    -0.45
     ¢
    -0.45
    POSITIVE LOGITS
    følge
    0.65
     goutte
    0.65
     quelcon
    0.61
     She
    0.60
     normaux
    0.59
     mourir
    0.58
     consiguiente
    0.58
     indépend
    0.58
     indépendante
    0.58
     Imagine
    0.57
    Activations Density 9.151%

    No Known Activations