© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 251207
    Prev
    Next
    INDEX
    Explanations

    being

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     done
    0.38
    done
    0.37
    Rena
    0.37
    㔹
    0.37
    ходят
    0.36
    ሽ
    0.35
    othic
    0.35
     Driving
    0.35
     осталось
    0.35
     стало
    0.34
    POSITIVE LOGITS
     being
    2.41
    being
    2.19
     Being
    2.19
    Being
    2.16
     BEING
    1.98
     sendo
    1.86
     étant
    1.73
     siendo
    1.71
     быть
    1.66
    被
    1.62
    Activations Density 0.013%

    No Known Activations