© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12448
    Prev
    Next
    INDEX
    Explanations

    mentions of curfews and their effects on people, places and things

    oai_token-act-pair · gemini-2.0-flash

    terms related to curfew and restriction

    np_token-act-pair-logits · gpt-4o-mini

    News events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     '\\;'
    -0.66
    omethane
    -0.63
    styleType
    -0.59
    tamo
    -0.50
    ]]);
    -0.50
    ganta
    -0.50
    '};
    -0.49
    Ход
    -0.49
    pless
    -0.49
    nestjs
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.71
    WriteBarrier
    0.65
    èvement
    0.58
    Spoljašnje
    0.56
    :✨
    0.54
     insuffisamment
    0.53
    setopt
    0.52
     distanciation
    0.51
    iconque
    0.50
     CiNii
    0.50
    Activations Density 6.605%

    No Known Activations