© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4247
    Prev
    Next
    INDEX
    Explanations

    uses of the preposition "on" and the preposition "for" along with some related words such as for 'the' or for 'this'.

    oai_token-act-pair · gemini-2.0-flash

    words with specific character patterns

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

    News and legal contexts

    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
    .
    -0.51
     ویکی‌پدی
    -0.50
    ,
    -0.50
    <eos>
    -0.47
     —
    -0.45
    ;
    -0.44
     the
    -0.44
     and
    -0.42
     it
    -0.41
    ↵↵
    -0.40
    POSITIVE LOGITS
    ſelves
    0.95
     faſt
    0.95
     tartalomajánló
    0.93
    ^(@)
    0.91
     pleaſure
    0.89
     purpoſe
    0.87
    ſelf
    0.86
     ſtate
    0.85
    Datuak
    0.84
     MainAxisSize
    0.83
    Activations Density 3.630%

    No Known Activations