© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129818
    Prev
    Next
    INDEX
    Explanations

    expensive or costly consequences

    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_1_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
     of
    1.41
    of
    1.30
    ल
    1.26
    ни
    1.09
    Y
    1.08
     של
    1.06
    kę
    0.99
     ")
    0.98
    .
    0.97
     ਇੱਕ
    0.95
    POSITIVE LOGITS
    t
    1.22
    را
    0.95
     rendement
    0.95
    孬
    0.94
    不已
    0.93
    返回
    0.91
     licenciatura
    0.89
    ம்
    0.87
    رك
    0.87
     financi
    0.87
    Activations Density 0.000%

    No Known Activations