© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12307
    Prev
    Next
    INDEX
    Explanations

    tokens containing "y"

    oai_token-act-pair · gemini-2.0-flash

    words starting with "y"

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

    Chemistry

    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
     <=",
    -1.02
     &___
    -1.00
     الحره
    -0.96
    ⓘ
    -0.96
    CloseOperation
    -0.94
     Roskov
    -0.93
    RegistryLite
    -0.93
    Билгалдахарш
    -0.92
    UnusedPrivate
    -0.91
    migrationBuilder
    -0.91
    POSITIVE LOGITS
    ai
    0.44
    th
    0.41
    r
    0.40
    d
    0.40
    Ab
    0.39
    no
    0.38
    ed
    0.37
    ab
    0.37
    able
    0.35
    ac
    0.35
    Activations Density 0.453%

    No Known Activations