© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2899
    Prev
    Next
    INDEX
    Explanations

    the phrase "soft serve" and other related words about the texture of food

    oai_token-act-pair · gemini-2.0-flash

    soft

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Disliked
    -0.48
     règlement
    -0.46
    Opinion
    -0.45
     lược
    -0.45
    éroport
    -0.45
    ší
    -0.43
    Ohne
    -0.43
    胜
    -0.42
     memer
    -0.41
     lubric
    -0.40
    POSITIVE LOGITS
    脚注の使い方
    0.82
     resourceCulture
    0.80
    tvguidetime
    0.72
    DeleteBehavior
    0.71
    IsContent
    0.70
    TagMode
    0.68
    UnusedPrivate
    0.66
     ]
    0.64
    Przypisy
    0.63
    SBATCH
    0.63
    Activations Density 0.876%

    No Known Activations