© 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-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52687
    Prev
    Next
    INDEX
    Explanations

    batch similar tasks, combine like terms

    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_30_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
    includ
    0.38
    }");
    0.37
    花了
    0.36
    ==="
    0.35
    hygine
    0.34
     हाइ
    0.33
    ڈین
    0.33
     confound
    0.33
    数据显示
    0.32
     hydroly
    0.32
    POSITIVE LOGITS
     отдельно
    0.51
     Separate
    0.43
     samostat
    0.41
    同
    0.40
     вместе
    0.39
     separate
    0.39
     따로
    0.39
     separately
    0.39
     самостоя
    0.38
     razem
    0.38
    Activations Density 0.007%

    No Known Activations