© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197817
    Prev
    Next
    INDEX
    Explanations

    names and references

    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_27_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
     받는
    0.37
     returned
    0.34
     increasingly
    0.34
     замі
    0.33
     peri
    0.32
    olata
    0.32
    複
    0.32
     complicated
    0.32
     इनके
    0.32
     Robot
    0.32
    POSITIVE LOGITS
     ассорти
    0.50
     predominance
    0.43
    }'],
    0.41
    ELE
    0.41
    すなわち
    0.41
     mandrel
    0.41
     centerpiece
    0.39
    currentNode
    0.38
    왤
    0.38
    繞
    0.37
    Activations Density 0.005%

    No Known Activations