© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1886
    Prev
    Next
    INDEX
    Explanations

    mentions of 'state-of-the-art' and 'algorithm' in a technical context.

    oai_token-act-pair · gemini-2.0-flash

    say "of"

    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
     state
    -3.02
    state
    -2.78
     State
    -2.73
    State
    -2.64
     STATE
    -2.55
    STATE
    -2.34
     states
    -2.00
     estado
    -1.97
     Estado
    -1.91
    getState
    -1.83
    POSITIVE LOGITS
     CanadaChoose
    0.65
    thenReturn
    0.50
    Datuak
    0.49
    lapsingToolbar
    0.48
    expandindo
    0.48
    fjspx
    0.48
     AssemblyCulture
    0.47
    ToBounds
    0.47
    期刊论文
    0.46
     Tert
    0.46
    Activations Density 4.890%

    No Known Activations