© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60110
    Prev
    Next
    INDEX
    Explanations

    elle endings

    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_2_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
    '
    1.41
     jonka
    1.04
    arten
    0.96
     добав
    0.89
    鶚
    0.87
    ্যারি
    0.84
    ಾರ
    0.84
     Daha
    0.83
     koska
    0.82
    AT
    0.82
    POSITIVE LOGITS
    ,
    1.48
    ق
    1.47
    ي
    1.39
    يه
    1.30
     to
    1.23
    ri
    1.23
    é
    1.20
    ig
    1.18
    да
    1.16
    q
    1.16
    Activations Density 0.000%

    No Known Activations