© 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. 12442
    Prev
    Next
    INDEX
    Explanations

    text about the persecution of Jews and about problems during the election

    oai_token-act-pair · gemini-2.0-flash

    actions associated with identification verification

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

    Access control

    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
     تضيفلها
    -0.97
    tagHelperRunner
    -0.93
    StoryboardSegue
    -0.93
    +#+#
    -0.91
    yntaxException
    -0.90
    ValueStyle
    -0.87
    LookAnd
    -0.83
    IsContent
    -0.81
     pleaſure
    -0.80
    Personendaten
    -0.77
    POSITIVE LOGITS
     scan
    0.63
     punch
    0.60
    scan
    0.57
    Scan
    0.53
    chip
    0.52
    punch
    0.51
     Scan
    0.49
     swipe
    0.48
    Punch
    0.47
    ID
    0.45
    Activations Density 1.642%

    No Known Activations