© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175095
    Prev
    Next
    INDEX
    Explanations

    reinforcing or reinforcement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MA
    0.43
     BEACH
    0.41
    OL
    0.40
    గర
    0.40
     highway
    0.40
    い
    0.39
    任
    0.39
     freeway
    0.39
     NAS
    0.38
     MA
    0.37
    POSITIVE LOGITS
     তালিকা
    0.48
    اونلو
    0.47
    Dates
    0.46
    டும்ப
    0.45
    Portuguese
    0.45
    fohlen
    0.45
     turnips
    0.45
    }}^{*
    0.44
    ૅ
    0.44
    ProductRunnable
    0.44
    Activations Density 0.001%

    No Known Activations