© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88924
    Prev
    Next
    INDEX
    Explanations

    electricity bill

    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_3_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
    ués
    0.68
    er
    0.61
    aldb
    0.60
     অনুষ্ঠ
    0.59
     scrapped
    0.59
    _),
    0.59
    леге
    0.58
    alisation
    0.57
    ية
    0.57
    lge
    0.56
    POSITIVE LOGITS
     It
    0.70
    टे
    0.66
     itu
    0.66
     daripada
    0.61
     it
    0.59
     Energy
    0.59
    :
    0.58
     pasti
    0.57
    MOUNTAINS
    0.57
     alat
    0.56
    Activations Density 0.001%

    No Known Activations